Ubuntu commited on
Commit
1e78866
1 Parent(s): ed03902
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - bn
4
+ license: apache-2.0
5
+ base_model: arun100/whisper-base-bn
6
+ tags:
7
+ - whisper-event
8
+ - generated_from_trainer
9
+ datasets:
10
+ - mozilla-foundation/common_voice_16_0
11
+ metrics:
12
+ - wer
13
+ model-index:
14
+ - name: Whisper Base Bengali
15
+ results:
16
+ - task:
17
+ name: Automatic Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: mozilla-foundation/common_voice_16_0 bn
21
+ type: mozilla-foundation/common_voice_16_0
22
+ config: bn
23
+ split: test
24
+ args: bn
25
+ metrics:
26
+ - name: Wer
27
+ type: wer
28
+ value: 35.60262364321316
29
+ ---
30
+
31
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
+ should probably proofread and complete it, then remove this comment. -->
33
+
34
+ # Whisper Base Bengali
35
+
36
+ This model is a fine-tuned version of [arun100/whisper-base-bn](https://huggingface.co/arun100/whisper-base-bn) on the mozilla-foundation/common_voice_16_0 bn dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.2671
39
+ - Wer: 35.6026
40
+
41
+ ## Model description
42
+
43
+ More information needed
44
+
45
+ ## Intended uses & limitations
46
+
47
+ More information needed
48
+
49
+ ## Training and evaluation data
50
+
51
+ More information needed
52
+
53
+ ## Training procedure
54
+
55
+ ### Training hyperparameters
56
+
57
+ The following hyperparameters were used during training:
58
+ - learning_rate: 1e-06
59
+ - train_batch_size: 32
60
+ - eval_batch_size: 32
61
+ - seed: 42
62
+ - gradient_accumulation_steps: 2
63
+ - total_train_batch_size: 64
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: linear
66
+ - lr_scheduler_warmup_steps: 50
67
+ - training_steps: 1000
68
+ - mixed_precision_training: Native AMP
69
+
70
+ ### Training results
71
+
72
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
73
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
74
+ | 0.2423 | 1.72 | 500 | 0.2710 | 35.9570 |
75
+ | 0.2329 | 3.43 | 1000 | 0.2671 | 35.6026 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.38.0.dev0
81
+ - Pytorch 2.1.2+cu121
82
+ - Datasets 2.16.2.dev0
83
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,1609 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|0.00|>": 50364,
3
+ "<|0.02|>": 50365,
4
+ "<|0.04|>": 50366,
5
+ "<|0.06|>": 50367,
6
+ "<|0.08|>": 50368,
7
+ "<|0.10|>": 50369,
8
+ "<|0.12|>": 50370,
9
+ "<|0.14|>": 50371,
10
+ "<|0.16|>": 50372,
11
+ "<|0.18|>": 50373,
12
+ "<|0.20|>": 50374,
13
+ "<|0.22|>": 50375,
14
+ "<|0.24|>": 50376,
15
+ "<|0.26|>": 50377,
16
+ "<|0.28|>": 50378,
17
+ "<|0.30|>": 50379,
18
+ "<|0.32|>": 50380,
19
+ "<|0.34|>": 50381,
20
+ "<|0.36|>": 50382,
21
+ "<|0.38|>": 50383,
22
+ "<|0.40|>": 50384,
23
+ "<|0.42|>": 50385,
24
+ "<|0.44|>": 50386,
25
+ "<|0.46|>": 50387,
26
+ "<|0.48|>": 50388,
27
+ "<|0.50|>": 50389,
28
+ "<|0.52|>": 50390,
29
+ "<|0.54|>": 50391,
30
+ "<|0.56|>": 50392,
31
+ "<|0.58|>": 50393,
32
+ "<|0.60|>": 50394,
33
+ "<|0.62|>": 50395,
34
+ "<|0.64|>": 50396,
35
+ "<|0.66|>": 50397,
36
+ "<|0.68|>": 50398,
37
+ "<|0.70|>": 50399,
38
+ "<|0.72|>": 50400,
39
+ "<|0.74|>": 50401,
40
+ "<|0.76|>": 50402,
41
+ "<|0.78|>": 50403,
42
+ "<|0.80|>": 50404,
43
+ "<|0.82|>": 50405,
44
+ "<|0.84|>": 50406,
45
+ "<|0.86|>": 50407,
46
+ "<|0.88|>": 50408,
47
+ "<|0.90|>": 50409,
48
+ "<|0.92|>": 50410,
49
+ "<|0.94|>": 50411,
50
+ "<|0.96|>": 50412,
51
+ "<|0.98|>": 50413,
52
+ "<|1.00|>": 50414,
53
+ "<|1.02|>": 50415,
54
+ "<|1.04|>": 50416,
55
+ "<|1.06|>": 50417,
56
+ "<|1.08|>": 50418,
57
+ "<|1.10|>": 50419,
58
+ "<|1.12|>": 50420,
59
+ "<|1.14|>": 50421,
60
+ "<|1.16|>": 50422,
61
+ "<|1.18|>": 50423,
62
+ "<|1.20|>": 50424,
63
+ "<|1.22|>": 50425,
64
+ "<|1.24|>": 50426,
65
+ "<|1.26|>": 50427,
66
+ "<|1.28|>": 50428,
67
+ "<|1.30|>": 50429,
68
+ "<|1.32|>": 50430,
69
+ "<|1.34|>": 50431,
70
+ "<|1.36|>": 50432,
71
+ "<|1.38|>": 50433,
72
+ "<|1.40|>": 50434,
73
+ "<|1.42|>": 50435,
74
+ "<|1.44|>": 50436,
75
+ "<|1.46|>": 50437,
76
+ "<|1.48|>": 50438,
77
+ "<|1.50|>": 50439,
78
+ "<|1.52|>": 50440,
79
+ "<|1.54|>": 50441,
80
+ "<|1.56|>": 50442,
81
+ "<|1.58|>": 50443,
82
+ "<|1.60|>": 50444,
83
+ "<|1.62|>": 50445,
84
+ "<|1.64|>": 50446,
85
+ "<|1.66|>": 50447,
86
+ "<|1.68|>": 50448,
87
+ "<|1.70|>": 50449,
88
+ "<|1.72|>": 50450,
89
+ "<|1.74|>": 50451,
90
+ "<|1.76|>": 50452,
91
+ "<|1.78|>": 50453,
92
+ "<|1.80|>": 50454,
93
+ "<|1.82|>": 50455,
94
+ "<|1.84|>": 50456,
95
+ "<|1.86|>": 50457,
96
+ "<|1.88|>": 50458,
97
+ "<|1.90|>": 50459,
98
+ "<|1.92|>": 50460,
99
+ "<|1.94|>": 50461,
100
+ "<|1.96|>": 50462,
101
+ "<|1.98|>": 50463,
102
+ "<|10.00|>": 50864,
103
+ "<|10.02|>": 50865,
104
+ "<|10.04|>": 50866,
105
+ "<|10.06|>": 50867,
106
+ "<|10.08|>": 50868,
107
+ "<|10.10|>": 50869,
108
+ "<|10.12|>": 50870,
109
+ "<|10.14|>": 50871,
110
+ "<|10.16|>": 50872,
111
+ "<|10.18|>": 50873,
112
+ "<|10.20|>": 50874,
113
+ "<|10.22|>": 50875,
114
+ "<|10.24|>": 50876,
115
+ "<|10.26|>": 50877,
116
+ "<|10.28|>": 50878,
117
+ "<|10.30|>": 50879,
118
+ "<|10.32|>": 50880,
119
+ "<|10.34|>": 50881,
120
+ "<|10.36|>": 50882,
121
+ "<|10.38|>": 50883,
122
+ "<|10.40|>": 50884,
123
+ "<|10.42|>": 50885,
124
+ "<|10.44|>": 50886,
125
+ "<|10.46|>": 50887,
126
+ "<|10.48|>": 50888,
127
+ "<|10.50|>": 50889,
128
+ "<|10.52|>": 50890,
129
+ "<|10.54|>": 50891,
130
+ "<|10.56|>": 50892,
131
+ "<|10.58|>": 50893,
132
+ "<|10.60|>": 50894,
133
+ "<|10.62|>": 50895,
134
+ "<|10.64|>": 50896,
135
+ "<|10.66|>": 50897,
136
+ "<|10.68|>": 50898,
137
+ "<|10.70|>": 50899,
138
+ "<|10.72|>": 50900,
139
+ "<|10.74|>": 50901,
140
+ "<|10.76|>": 50902,
141
+ "<|10.78|>": 50903,
142
+ "<|10.80|>": 50904,
143
+ "<|10.82|>": 50905,
144
+ "<|10.84|>": 50906,
145
+ "<|10.86|>": 50907,
146
+ "<|10.88|>": 50908,
147
+ "<|10.90|>": 50909,
148
+ "<|10.92|>": 50910,
149
+ "<|10.94|>": 50911,
150
+ "<|10.96|>": 50912,
151
+ "<|10.98|>": 50913,
152
+ "<|11.00|>": 50914,
153
+ "<|11.02|>": 50915,
154
+ "<|11.04|>": 50916,
155
+ "<|11.06|>": 50917,
156
+ "<|11.08|>": 50918,
157
+ "<|11.10|>": 50919,
158
+ "<|11.12|>": 50920,
159
+ "<|11.14|>": 50921,
160
+ "<|11.16|>": 50922,
161
+ "<|11.18|>": 50923,
162
+ "<|11.20|>": 50924,
163
+ "<|11.22|>": 50925,
164
+ "<|11.24|>": 50926,
165
+ "<|11.26|>": 50927,
166
+ "<|11.28|>": 50928,
167
+ "<|11.30|>": 50929,
168
+ "<|11.32|>": 50930,
169
+ "<|11.34|>": 50931,
170
+ "<|11.36|>": 50932,
171
+ "<|11.38|>": 50933,
172
+ "<|11.40|>": 50934,
173
+ "<|11.42|>": 50935,
174
+ "<|11.44|>": 50936,
175
+ "<|11.46|>": 50937,
176
+ "<|11.48|>": 50938,
177
+ "<|11.50|>": 50939,
178
+ "<|11.52|>": 50940,
179
+ "<|11.54|>": 50941,
180
+ "<|11.56|>": 50942,
181
+ "<|11.58|>": 50943,
182
+ "<|11.60|>": 50944,
183
+ "<|11.62|>": 50945,
184
+ "<|11.64|>": 50946,
185
+ "<|11.66|>": 50947,
186
+ "<|11.68|>": 50948,
187
+ "<|11.70|>": 50949,
188
+ "<|11.72|>": 50950,
189
+ "<|11.74|>": 50951,
190
+ "<|11.76|>": 50952,
191
+ "<|11.78|>": 50953,
192
+ "<|11.80|>": 50954,
193
+ "<|11.82|>": 50955,
194
+ "<|11.84|>": 50956,
195
+ "<|11.86|>": 50957,
196
+ "<|11.88|>": 50958,
197
+ "<|11.90|>": 50959,
198
+ "<|11.92|>": 50960,
199
+ "<|11.94|>": 50961,
200
+ "<|11.96|>": 50962,
201
+ "<|11.98|>": 50963,
202
+ "<|12.00|>": 50964,
203
+ "<|12.02|>": 50965,
204
+ "<|12.04|>": 50966,
205
+ "<|12.06|>": 50967,
206
+ "<|12.08|>": 50968,
207
+ "<|12.10|>": 50969,
208
+ "<|12.12|>": 50970,
209
+ "<|12.14|>": 50971,
210
+ "<|12.16|>": 50972,
211
+ "<|12.18|>": 50973,
212
+ "<|12.20|>": 50974,
213
+ "<|12.22|>": 50975,
214
+ "<|12.24|>": 50976,
215
+ "<|12.26|>": 50977,
216
+ "<|12.28|>": 50978,
217
+ "<|12.30|>": 50979,
218
+ "<|12.32|>": 50980,
219
+ "<|12.34|>": 50981,
220
+ "<|12.36|>": 50982,
221
+ "<|12.38|>": 50983,
222
+ "<|12.40|>": 50984,
223
+ "<|12.42|>": 50985,
224
+ "<|12.44|>": 50986,
225
+ "<|12.46|>": 50987,
226
+ "<|12.48|>": 50988,
227
+ "<|12.50|>": 50989,
228
+ "<|12.52|>": 50990,
229
+ "<|12.54|>": 50991,
230
+ "<|12.56|>": 50992,
231
+ "<|12.58|>": 50993,
232
+ "<|12.60|>": 50994,
233
+ "<|12.62|>": 50995,
234
+ "<|12.64|>": 50996,
235
+ "<|12.66|>": 50997,
236
+ "<|12.68|>": 50998,
237
+ "<|12.70|>": 50999,
238
+ "<|12.72|>": 51000,
239
+ "<|12.74|>": 51001,
240
+ "<|12.76|>": 51002,
241
+ "<|12.78|>": 51003,
242
+ "<|12.80|>": 51004,
243
+ "<|12.82|>": 51005,
244
+ "<|12.84|>": 51006,
245
+ "<|12.86|>": 51007,
246
+ "<|12.88|>": 51008,
247
+ "<|12.90|>": 51009,
248
+ "<|12.92|>": 51010,
249
+ "<|12.94|>": 51011,
250
+ "<|12.96|>": 51012,
251
+ "<|12.98|>": 51013,
252
+ "<|13.00|>": 51014,
253
+ "<|13.02|>": 51015,
254
+ "<|13.04|>": 51016,
255
+ "<|13.06|>": 51017,
256
+ "<|13.08|>": 51018,
257
+ "<|13.10|>": 51019,
258
+ "<|13.12|>": 51020,
259
+ "<|13.14|>": 51021,
260
+ "<|13.16|>": 51022,
261
+ "<|13.18|>": 51023,
262
+ "<|13.20|>": 51024,
263
+ "<|13.22|>": 51025,
264
+ "<|13.24|>": 51026,
265
+ "<|13.26|>": 51027,
266
+ "<|13.28|>": 51028,
267
+ "<|13.30|>": 51029,
268
+ "<|13.32|>": 51030,
269
+ "<|13.34|>": 51031,
270
+ "<|13.36|>": 51032,
271
+ "<|13.38|>": 51033,
272
+ "<|13.40|>": 51034,
273
+ "<|13.42|>": 51035,
274
+ "<|13.44|>": 51036,
275
+ "<|13.46|>": 51037,
276
+ "<|13.48|>": 51038,
277
+ "<|13.50|>": 51039,
278
+ "<|13.52|>": 51040,
279
+ "<|13.54|>": 51041,
280
+ "<|13.56|>": 51042,
281
+ "<|13.58|>": 51043,
282
+ "<|13.60|>": 51044,
283
+ "<|13.62|>": 51045,
284
+ "<|13.64|>": 51046,
285
+ "<|13.66|>": 51047,
286
+ "<|13.68|>": 51048,
287
+ "<|13.70|>": 51049,
288
+ "<|13.72|>": 51050,
289
+ "<|13.74|>": 51051,
290
+ "<|13.76|>": 51052,
291
+ "<|13.78|>": 51053,
292
+ "<|13.80|>": 51054,
293
+ "<|13.82|>": 51055,
294
+ "<|13.84|>": 51056,
295
+ "<|13.86|>": 51057,
296
+ "<|13.88|>": 51058,
297
+ "<|13.90|>": 51059,
298
+ "<|13.92|>": 51060,
299
+ "<|13.94|>": 51061,
300
+ "<|13.96|>": 51062,
301
+ "<|13.98|>": 51063,
302
+ "<|14.00|>": 51064,
303
+ "<|14.02|>": 51065,
304
+ "<|14.04|>": 51066,
305
+ "<|14.06|>": 51067,
306
+ "<|14.08|>": 51068,
307
+ "<|14.10|>": 51069,
308
+ "<|14.12|>": 51070,
309
+ "<|14.14|>": 51071,
310
+ "<|14.16|>": 51072,
311
+ "<|14.18|>": 51073,
312
+ "<|14.20|>": 51074,
313
+ "<|14.22|>": 51075,
314
+ "<|14.24|>": 51076,
315
+ "<|14.26|>": 51077,
316
+ "<|14.28|>": 51078,
317
+ "<|14.30|>": 51079,
318
+ "<|14.32|>": 51080,
319
+ "<|14.34|>": 51081,
320
+ "<|14.36|>": 51082,
321
+ "<|14.38|>": 51083,
322
+ "<|14.40|>": 51084,
323
+ "<|14.42|>": 51085,
324
+ "<|14.44|>": 51086,
325
+ "<|14.46|>": 51087,
326
+ "<|14.48|>": 51088,
327
+ "<|14.50|>": 51089,
328
+ "<|14.52|>": 51090,
329
+ "<|14.54|>": 51091,
330
+ "<|14.56|>": 51092,
331
+ "<|14.58|>": 51093,
332
+ "<|14.60|>": 51094,
333
+ "<|14.62|>": 51095,
334
+ "<|14.64|>": 51096,
335
+ "<|14.66|>": 51097,
336
+ "<|14.68|>": 51098,
337
+ "<|14.70|>": 51099,
338
+ "<|14.72|>": 51100,
339
+ "<|14.74|>": 51101,
340
+ "<|14.76|>": 51102,
341
+ "<|14.78|>": 51103,
342
+ "<|14.80|>": 51104,
343
+ "<|14.82|>": 51105,
344
+ "<|14.84|>": 51106,
345
+ "<|14.86|>": 51107,
346
+ "<|14.88|>": 51108,
347
+ "<|14.90|>": 51109,
348
+ "<|14.92|>": 51110,
349
+ "<|14.94|>": 51111,
350
+ "<|14.96|>": 51112,
351
+ "<|14.98|>": 51113,
352
+ "<|15.00|>": 51114,
353
+ "<|15.02|>": 51115,
354
+ "<|15.04|>": 51116,
355
+ "<|15.06|>": 51117,
356
+ "<|15.08|>": 51118,
357
+ "<|15.10|>": 51119,
358
+ "<|15.12|>": 51120,
359
+ "<|15.14|>": 51121,
360
+ "<|15.16|>": 51122,
361
+ "<|15.18|>": 51123,
362
+ "<|15.20|>": 51124,
363
+ "<|15.22|>": 51125,
364
+ "<|15.24|>": 51126,
365
+ "<|15.26|>": 51127,
366
+ "<|15.28|>": 51128,
367
+ "<|15.30|>": 51129,
368
+ "<|15.32|>": 51130,
369
+ "<|15.34|>": 51131,
370
+ "<|15.36|>": 51132,
371
+ "<|15.38|>": 51133,
372
+ "<|15.40|>": 51134,
373
+ "<|15.42|>": 51135,
374
+ "<|15.44|>": 51136,
375
+ "<|15.46|>": 51137,
376
+ "<|15.48|>": 51138,
377
+ "<|15.50|>": 51139,
378
+ "<|15.52|>": 51140,
379
+ "<|15.54|>": 51141,
380
+ "<|15.56|>": 51142,
381
+ "<|15.58|>": 51143,
382
+ "<|15.60|>": 51144,
383
+ "<|15.62|>": 51145,
384
+ "<|15.64|>": 51146,
385
+ "<|15.66|>": 51147,
386
+ "<|15.68|>": 51148,
387
+ "<|15.70|>": 51149,
388
+ "<|15.72|>": 51150,
389
+ "<|15.74|>": 51151,
390
+ "<|15.76|>": 51152,
391
+ "<|15.78|>": 51153,
392
+ "<|15.80|>": 51154,
393
+ "<|15.82|>": 51155,
394
+ "<|15.84|>": 51156,
395
+ "<|15.86|>": 51157,
396
+ "<|15.88|>": 51158,
397
+ "<|15.90|>": 51159,
398
+ "<|15.92|>": 51160,
399
+ "<|15.94|>": 51161,
400
+ "<|15.96|>": 51162,
401
+ "<|15.98|>": 51163,
402
+ "<|16.00|>": 51164,
403
+ "<|16.02|>": 51165,
404
+ "<|16.04|>": 51166,
405
+ "<|16.06|>": 51167,
406
+ "<|16.08|>": 51168,
407
+ "<|16.10|>": 51169,
408
+ "<|16.12|>": 51170,
409
+ "<|16.14|>": 51171,
410
+ "<|16.16|>": 51172,
411
+ "<|16.18|>": 51173,
412
+ "<|16.20|>": 51174,
413
+ "<|16.22|>": 51175,
414
+ "<|16.24|>": 51176,
415
+ "<|16.26|>": 51177,
416
+ "<|16.28|>": 51178,
417
+ "<|16.30|>": 51179,
418
+ "<|16.32|>": 51180,
419
+ "<|16.34|>": 51181,
420
+ "<|16.36|>": 51182,
421
+ "<|16.38|>": 51183,
422
+ "<|16.40|>": 51184,
423
+ "<|16.42|>": 51185,
424
+ "<|16.44|>": 51186,
425
+ "<|16.46|>": 51187,
426
+ "<|16.48|>": 51188,
427
+ "<|16.50|>": 51189,
428
+ "<|16.52|>": 51190,
429
+ "<|16.54|>": 51191,
430
+ "<|16.56|>": 51192,
431
+ "<|16.58|>": 51193,
432
+ "<|16.60|>": 51194,
433
+ "<|16.62|>": 51195,
434
+ "<|16.64|>": 51196,
435
+ "<|16.66|>": 51197,
436
+ "<|16.68|>": 51198,
437
+ "<|16.70|>": 51199,
438
+ "<|16.72|>": 51200,
439
+ "<|16.74|>": 51201,
440
+ "<|16.76|>": 51202,
441
+ "<|16.78|>": 51203,
442
+ "<|16.80|>": 51204,
443
+ "<|16.82|>": 51205,
444
+ "<|16.84|>": 51206,
445
+ "<|16.86|>": 51207,
446
+ "<|16.88|>": 51208,
447
+ "<|16.90|>": 51209,
448
+ "<|16.92|>": 51210,
449
+ "<|16.94|>": 51211,
450
+ "<|16.96|>": 51212,
451
+ "<|16.98|>": 51213,
452
+ "<|17.00|>": 51214,
453
+ "<|17.02|>": 51215,
454
+ "<|17.04|>": 51216,
455
+ "<|17.06|>": 51217,
456
+ "<|17.08|>": 51218,
457
+ "<|17.10|>": 51219,
458
+ "<|17.12|>": 51220,
459
+ "<|17.14|>": 51221,
460
+ "<|17.16|>": 51222,
461
+ "<|17.18|>": 51223,
462
+ "<|17.20|>": 51224,
463
+ "<|17.22|>": 51225,
464
+ "<|17.24|>": 51226,
465
+ "<|17.26|>": 51227,
466
+ "<|17.28|>": 51228,
467
+ "<|17.30|>": 51229,
468
+ "<|17.32|>": 51230,
469
+ "<|17.34|>": 51231,
470
+ "<|17.36|>": 51232,
471
+ "<|17.38|>": 51233,
472
+ "<|17.40|>": 51234,
473
+ "<|17.42|>": 51235,
474
+ "<|17.44|>": 51236,
475
+ "<|17.46|>": 51237,
476
+ "<|17.48|>": 51238,
477
+ "<|17.50|>": 51239,
478
+ "<|17.52|>": 51240,
479
+ "<|17.54|>": 51241,
480
+ "<|17.56|>": 51242,
481
+ "<|17.58|>": 51243,
482
+ "<|17.60|>": 51244,
483
+ "<|17.62|>": 51245,
484
+ "<|17.64|>": 51246,
485
+ "<|17.66|>": 51247,
486
+ "<|17.68|>": 51248,
487
+ "<|17.70|>": 51249,
488
+ "<|17.72|>": 51250,
489
+ "<|17.74|>": 51251,
490
+ "<|17.76|>": 51252,
491
+ "<|17.78|>": 51253,
492
+ "<|17.80|>": 51254,
493
+ "<|17.82|>": 51255,
494
+ "<|17.84|>": 51256,
495
+ "<|17.86|>": 51257,
496
+ "<|17.88|>": 51258,
497
+ "<|17.90|>": 51259,
498
+ "<|17.92|>": 51260,
499
+ "<|17.94|>": 51261,
500
+ "<|17.96|>": 51262,
501
+ "<|17.98|>": 51263,
502
+ "<|18.00|>": 51264,
503
+ "<|18.02|>": 51265,
504
+ "<|18.04|>": 51266,
505
+ "<|18.06|>": 51267,
506
+ "<|18.08|>": 51268,
507
+ "<|18.10|>": 51269,
508
+ "<|18.12|>": 51270,
509
+ "<|18.14|>": 51271,
510
+ "<|18.16|>": 51272,
511
+ "<|18.18|>": 51273,
512
+ "<|18.20|>": 51274,
513
+ "<|18.22|>": 51275,
514
+ "<|18.24|>": 51276,
515
+ "<|18.26|>": 51277,
516
+ "<|18.28|>": 51278,
517
+ "<|18.30|>": 51279,
518
+ "<|18.32|>": 51280,
519
+ "<|18.34|>": 51281,
520
+ "<|18.36|>": 51282,
521
+ "<|18.38|>": 51283,
522
+ "<|18.40|>": 51284,
523
+ "<|18.42|>": 51285,
524
+ "<|18.44|>": 51286,
525
+ "<|18.46|>": 51287,
526
+ "<|18.48|>": 51288,
527
+ "<|18.50|>": 51289,
528
+ "<|18.52|>": 51290,
529
+ "<|18.54|>": 51291,
530
+ "<|18.56|>": 51292,
531
+ "<|18.58|>": 51293,
532
+ "<|18.60|>": 51294,
533
+ "<|18.62|>": 51295,
534
+ "<|18.64|>": 51296,
535
+ "<|18.66|>": 51297,
536
+ "<|18.68|>": 51298,
537
+ "<|18.70|>": 51299,
538
+ "<|18.72|>": 51300,
539
+ "<|18.74|>": 51301,
540
+ "<|18.76|>": 51302,
541
+ "<|18.78|>": 51303,
542
+ "<|18.80|>": 51304,
543
+ "<|18.82|>": 51305,
544
+ "<|18.84|>": 51306,
545
+ "<|18.86|>": 51307,
546
+ "<|18.88|>": 51308,
547
+ "<|18.90|>": 51309,
548
+ "<|18.92|>": 51310,
549
+ "<|18.94|>": 51311,
550
+ "<|18.96|>": 51312,
551
+ "<|18.98|>": 51313,
552
+ "<|19.00|>": 51314,
553
+ "<|19.02|>": 51315,
554
+ "<|19.04|>": 51316,
555
+ "<|19.06|>": 51317,
556
+ "<|19.08|>": 51318,
557
+ "<|19.10|>": 51319,
558
+ "<|19.12|>": 51320,
559
+ "<|19.14|>": 51321,
560
+ "<|19.16|>": 51322,
561
+ "<|19.18|>": 51323,
562
+ "<|19.20|>": 51324,
563
+ "<|19.22|>": 51325,
564
+ "<|19.24|>": 51326,
565
+ "<|19.26|>": 51327,
566
+ "<|19.28|>": 51328,
567
+ "<|19.30|>": 51329,
568
+ "<|19.32|>": 51330,
569
+ "<|19.34|>": 51331,
570
+ "<|19.36|>": 51332,
571
+ "<|19.38|>": 51333,
572
+ "<|19.40|>": 51334,
573
+ "<|19.42|>": 51335,
574
+ "<|19.44|>": 51336,
575
+ "<|19.46|>": 51337,
576
+ "<|19.48|>": 51338,
577
+ "<|19.50|>": 51339,
578
+ "<|19.52|>": 51340,
579
+ "<|19.54|>": 51341,
580
+ "<|19.56|>": 51342,
581
+ "<|19.58|>": 51343,
582
+ "<|19.60|>": 51344,
583
+ "<|19.62|>": 51345,
584
+ "<|19.64|>": 51346,
585
+ "<|19.66|>": 51347,
586
+ "<|19.68|>": 51348,
587
+ "<|19.70|>": 51349,
588
+ "<|19.72|>": 51350,
589
+ "<|19.74|>": 51351,
590
+ "<|19.76|>": 51352,
591
+ "<|19.78|>": 51353,
592
+ "<|19.80|>": 51354,
593
+ "<|19.82|>": 51355,
594
+ "<|19.84|>": 51356,
595
+ "<|19.86|>": 51357,
596
+ "<|19.88|>": 51358,
597
+ "<|19.90|>": 51359,
598
+ "<|19.92|>": 51360,
599
+ "<|19.94|>": 51361,
600
+ "<|19.96|>": 51362,
601
+ "<|19.98|>": 51363,
602
+ "<|2.00|>": 50464,
603
+ "<|2.02|>": 50465,
604
+ "<|2.04|>": 50466,
605
+ "<|2.06|>": 50467,
606
+ "<|2.08|>": 50468,
607
+ "<|2.10|>": 50469,
608
+ "<|2.12|>": 50470,
609
+ "<|2.14|>": 50471,
610
+ "<|2.16|>": 50472,
611
+ "<|2.18|>": 50473,
612
+ "<|2.20|>": 50474,
613
+ "<|2.22|>": 50475,
614
+ "<|2.24|>": 50476,
615
+ "<|2.26|>": 50477,
616
+ "<|2.28|>": 50478,
617
+ "<|2.30|>": 50479,
618
+ "<|2.32|>": 50480,
619
+ "<|2.34|>": 50481,
620
+ "<|2.36|>": 50482,
621
+ "<|2.38|>": 50483,
622
+ "<|2.40|>": 50484,
623
+ "<|2.42|>": 50485,
624
+ "<|2.44|>": 50486,
625
+ "<|2.46|>": 50487,
626
+ "<|2.48|>": 50488,
627
+ "<|2.50|>": 50489,
628
+ "<|2.52|>": 50490,
629
+ "<|2.54|>": 50491,
630
+ "<|2.56|>": 50492,
631
+ "<|2.58|>": 50493,
632
+ "<|2.60|>": 50494,
633
+ "<|2.62|>": 50495,
634
+ "<|2.64|>": 50496,
635
+ "<|2.66|>": 50497,
636
+ "<|2.68|>": 50498,
637
+ "<|2.70|>": 50499,
638
+ "<|2.72|>": 50500,
639
+ "<|2.74|>": 50501,
640
+ "<|2.76|>": 50502,
641
+ "<|2.78|>": 50503,
642
+ "<|2.80|>": 50504,
643
+ "<|2.82|>": 50505,
644
+ "<|2.84|>": 50506,
645
+ "<|2.86|>": 50507,
646
+ "<|2.88|>": 50508,
647
+ "<|2.90|>": 50509,
648
+ "<|2.92|>": 50510,
649
+ "<|2.94|>": 50511,
650
+ "<|2.96|>": 50512,
651
+ "<|2.98|>": 50513,
652
+ "<|20.00|>": 51364,
653
+ "<|20.02|>": 51365,
654
+ "<|20.04|>": 51366,
655
+ "<|20.06|>": 51367,
656
+ "<|20.08|>": 51368,
657
+ "<|20.10|>": 51369,
658
+ "<|20.12|>": 51370,
659
+ "<|20.14|>": 51371,
660
+ "<|20.16|>": 51372,
661
+ "<|20.18|>": 51373,
662
+ "<|20.20|>": 51374,
663
+ "<|20.22|>": 51375,
664
+ "<|20.24|>": 51376,
665
+ "<|20.26|>": 51377,
666
+ "<|20.28|>": 51378,
667
+ "<|20.30|>": 51379,
668
+ "<|20.32|>": 51380,
669
+ "<|20.34|>": 51381,
670
+ "<|20.36|>": 51382,
671
+ "<|20.38|>": 51383,
672
+ "<|20.40|>": 51384,
673
+ "<|20.42|>": 51385,
674
+ "<|20.44|>": 51386,
675
+ "<|20.46|>": 51387,
676
+ "<|20.48|>": 51388,
677
+ "<|20.50|>": 51389,
678
+ "<|20.52|>": 51390,
679
+ "<|20.54|>": 51391,
680
+ "<|20.56|>": 51392,
681
+ "<|20.58|>": 51393,
682
+ "<|20.60|>": 51394,
683
+ "<|20.62|>": 51395,
684
+ "<|20.64|>": 51396,
685
+ "<|20.66|>": 51397,
686
+ "<|20.68|>": 51398,
687
+ "<|20.70|>": 51399,
688
+ "<|20.72|>": 51400,
689
+ "<|20.74|>": 51401,
690
+ "<|20.76|>": 51402,
691
+ "<|20.78|>": 51403,
692
+ "<|20.80|>": 51404,
693
+ "<|20.82|>": 51405,
694
+ "<|20.84|>": 51406,
695
+ "<|20.86|>": 51407,
696
+ "<|20.88|>": 51408,
697
+ "<|20.90|>": 51409,
698
+ "<|20.92|>": 51410,
699
+ "<|20.94|>": 51411,
700
+ "<|20.96|>": 51412,
701
+ "<|20.98|>": 51413,
702
+ "<|21.00|>": 51414,
703
+ "<|21.02|>": 51415,
704
+ "<|21.04|>": 51416,
705
+ "<|21.06|>": 51417,
706
+ "<|21.08|>": 51418,
707
+ "<|21.10|>": 51419,
708
+ "<|21.12|>": 51420,
709
+ "<|21.14|>": 51421,
710
+ "<|21.16|>": 51422,
711
+ "<|21.18|>": 51423,
712
+ "<|21.20|>": 51424,
713
+ "<|21.22|>": 51425,
714
+ "<|21.24|>": 51426,
715
+ "<|21.26|>": 51427,
716
+ "<|21.28|>": 51428,
717
+ "<|21.30|>": 51429,
718
+ "<|21.32|>": 51430,
719
+ "<|21.34|>": 51431,
720
+ "<|21.36|>": 51432,
721
+ "<|21.38|>": 51433,
722
+ "<|21.40|>": 51434,
723
+ "<|21.42|>": 51435,
724
+ "<|21.44|>": 51436,
725
+ "<|21.46|>": 51437,
726
+ "<|21.48|>": 51438,
727
+ "<|21.50|>": 51439,
728
+ "<|21.52|>": 51440,
729
+ "<|21.54|>": 51441,
730
+ "<|21.56|>": 51442,
731
+ "<|21.58|>": 51443,
732
+ "<|21.60|>": 51444,
733
+ "<|21.62|>": 51445,
734
+ "<|21.64|>": 51446,
735
+ "<|21.66|>": 51447,
736
+ "<|21.68|>": 51448,
737
+ "<|21.70|>": 51449,
738
+ "<|21.72|>": 51450,
739
+ "<|21.74|>": 51451,
740
+ "<|21.76|>": 51452,
741
+ "<|21.78|>": 51453,
742
+ "<|21.80|>": 51454,
743
+ "<|21.82|>": 51455,
744
+ "<|21.84|>": 51456,
745
+ "<|21.86|>": 51457,
746
+ "<|21.88|>": 51458,
747
+ "<|21.90|>": 51459,
748
+ "<|21.92|>": 51460,
749
+ "<|21.94|>": 51461,
750
+ "<|21.96|>": 51462,
751
+ "<|21.98|>": 51463,
752
+ "<|22.00|>": 51464,
753
+ "<|22.02|>": 51465,
754
+ "<|22.04|>": 51466,
755
+ "<|22.06|>": 51467,
756
+ "<|22.08|>": 51468,
757
+ "<|22.10|>": 51469,
758
+ "<|22.12|>": 51470,
759
+ "<|22.14|>": 51471,
760
+ "<|22.16|>": 51472,
761
+ "<|22.18|>": 51473,
762
+ "<|22.20|>": 51474,
763
+ "<|22.22|>": 51475,
764
+ "<|22.24|>": 51476,
765
+ "<|22.26|>": 51477,
766
+ "<|22.28|>": 51478,
767
+ "<|22.30|>": 51479,
768
+ "<|22.32|>": 51480,
769
+ "<|22.34|>": 51481,
770
+ "<|22.36|>": 51482,
771
+ "<|22.38|>": 51483,
772
+ "<|22.40|>": 51484,
773
+ "<|22.42|>": 51485,
774
+ "<|22.44|>": 51486,
775
+ "<|22.46|>": 51487,
776
+ "<|22.48|>": 51488,
777
+ "<|22.50|>": 51489,
778
+ "<|22.52|>": 51490,
779
+ "<|22.54|>": 51491,
780
+ "<|22.56|>": 51492,
781
+ "<|22.58|>": 51493,
782
+ "<|22.60|>": 51494,
783
+ "<|22.62|>": 51495,
784
+ "<|22.64|>": 51496,
785
+ "<|22.66|>": 51497,
786
+ "<|22.68|>": 51498,
787
+ "<|22.70|>": 51499,
788
+ "<|22.72|>": 51500,
789
+ "<|22.74|>": 51501,
790
+ "<|22.76|>": 51502,
791
+ "<|22.78|>": 51503,
792
+ "<|22.80|>": 51504,
793
+ "<|22.82|>": 51505,
794
+ "<|22.84|>": 51506,
795
+ "<|22.86|>": 51507,
796
+ "<|22.88|>": 51508,
797
+ "<|22.90|>": 51509,
798
+ "<|22.92|>": 51510,
799
+ "<|22.94|>": 51511,
800
+ "<|22.96|>": 51512,
801
+ "<|22.98|>": 51513,
802
+ "<|23.00|>": 51514,
803
+ "<|23.02|>": 51515,
804
+ "<|23.04|>": 51516,
805
+ "<|23.06|>": 51517,
806
+ "<|23.08|>": 51518,
807
+ "<|23.10|>": 51519,
808
+ "<|23.12|>": 51520,
809
+ "<|23.14|>": 51521,
810
+ "<|23.16|>": 51522,
811
+ "<|23.18|>": 51523,
812
+ "<|23.20|>": 51524,
813
+ "<|23.22|>": 51525,
814
+ "<|23.24|>": 51526,
815
+ "<|23.26|>": 51527,
816
+ "<|23.28|>": 51528,
817
+ "<|23.30|>": 51529,
818
+ "<|23.32|>": 51530,
819
+ "<|23.34|>": 51531,
820
+ "<|23.36|>": 51532,
821
+ "<|23.38|>": 51533,
822
+ "<|23.40|>": 51534,
823
+ "<|23.42|>": 51535,
824
+ "<|23.44|>": 51536,
825
+ "<|23.46|>": 51537,
826
+ "<|23.48|>": 51538,
827
+ "<|23.50|>": 51539,
828
+ "<|23.52|>": 51540,
829
+ "<|23.54|>": 51541,
830
+ "<|23.56|>": 51542,
831
+ "<|23.58|>": 51543,
832
+ "<|23.60|>": 51544,
833
+ "<|23.62|>": 51545,
834
+ "<|23.64|>": 51546,
835
+ "<|23.66|>": 51547,
836
+ "<|23.68|>": 51548,
837
+ "<|23.70|>": 51549,
838
+ "<|23.72|>": 51550,
839
+ "<|23.74|>": 51551,
840
+ "<|23.76|>": 51552,
841
+ "<|23.78|>": 51553,
842
+ "<|23.80|>": 51554,
843
+ "<|23.82|>": 51555,
844
+ "<|23.84|>": 51556,
845
+ "<|23.86|>": 51557,
846
+ "<|23.88|>": 51558,
847
+ "<|23.90|>": 51559,
848
+ "<|23.92|>": 51560,
849
+ "<|23.94|>": 51561,
850
+ "<|23.96|>": 51562,
851
+ "<|23.98|>": 51563,
852
+ "<|24.00|>": 51564,
853
+ "<|24.02|>": 51565,
854
+ "<|24.04|>": 51566,
855
+ "<|24.06|>": 51567,
856
+ "<|24.08|>": 51568,
857
+ "<|24.10|>": 51569,
858
+ "<|24.12|>": 51570,
859
+ "<|24.14|>": 51571,
860
+ "<|24.16|>": 51572,
861
+ "<|24.18|>": 51573,
862
+ "<|24.20|>": 51574,
863
+ "<|24.22|>": 51575,
864
+ "<|24.24|>": 51576,
865
+ "<|24.26|>": 51577,
866
+ "<|24.28|>": 51578,
867
+ "<|24.30|>": 51579,
868
+ "<|24.32|>": 51580,
869
+ "<|24.34|>": 51581,
870
+ "<|24.36|>": 51582,
871
+ "<|24.38|>": 51583,
872
+ "<|24.40|>": 51584,
873
+ "<|24.42|>": 51585,
874
+ "<|24.44|>": 51586,
875
+ "<|24.46|>": 51587,
876
+ "<|24.48|>": 51588,
877
+ "<|24.50|>": 51589,
878
+ "<|24.52|>": 51590,
879
+ "<|24.54|>": 51591,
880
+ "<|24.56|>": 51592,
881
+ "<|24.58|>": 51593,
882
+ "<|24.60|>": 51594,
883
+ "<|24.62|>": 51595,
884
+ "<|24.64|>": 51596,
885
+ "<|24.66|>": 51597,
886
+ "<|24.68|>": 51598,
887
+ "<|24.70|>": 51599,
888
+ "<|24.72|>": 51600,
889
+ "<|24.74|>": 51601,
890
+ "<|24.76|>": 51602,
891
+ "<|24.78|>": 51603,
892
+ "<|24.80|>": 51604,
893
+ "<|24.82|>": 51605,
894
+ "<|24.84|>": 51606,
895
+ "<|24.86|>": 51607,
896
+ "<|24.88|>": 51608,
897
+ "<|24.90|>": 51609,
898
+ "<|24.92|>": 51610,
899
+ "<|24.94|>": 51611,
900
+ "<|24.96|>": 51612,
901
+ "<|24.98|>": 51613,
902
+ "<|25.00|>": 51614,
903
+ "<|25.02|>": 51615,
904
+ "<|25.04|>": 51616,
905
+ "<|25.06|>": 51617,
906
+ "<|25.08|>": 51618,
907
+ "<|25.10|>": 51619,
908
+ "<|25.12|>": 51620,
909
+ "<|25.14|>": 51621,
910
+ "<|25.16|>": 51622,
911
+ "<|25.18|>": 51623,
912
+ "<|25.20|>": 51624,
913
+ "<|25.22|>": 51625,
914
+ "<|25.24|>": 51626,
915
+ "<|25.26|>": 51627,
916
+ "<|25.28|>": 51628,
917
+ "<|25.30|>": 51629,
918
+ "<|25.32|>": 51630,
919
+ "<|25.34|>": 51631,
920
+ "<|25.36|>": 51632,
921
+ "<|25.38|>": 51633,
922
+ "<|25.40|>": 51634,
923
+ "<|25.42|>": 51635,
924
+ "<|25.44|>": 51636,
925
+ "<|25.46|>": 51637,
926
+ "<|25.48|>": 51638,
927
+ "<|25.50|>": 51639,
928
+ "<|25.52|>": 51640,
929
+ "<|25.54|>": 51641,
930
+ "<|25.56|>": 51642,
931
+ "<|25.58|>": 51643,
932
+ "<|25.60|>": 51644,
933
+ "<|25.62|>": 51645,
934
+ "<|25.64|>": 51646,
935
+ "<|25.66|>": 51647,
936
+ "<|25.68|>": 51648,
937
+ "<|25.70|>": 51649,
938
+ "<|25.72|>": 51650,
939
+ "<|25.74|>": 51651,
940
+ "<|25.76|>": 51652,
941
+ "<|25.78|>": 51653,
942
+ "<|25.80|>": 51654,
943
+ "<|25.82|>": 51655,
944
+ "<|25.84|>": 51656,
945
+ "<|25.86|>": 51657,
946
+ "<|25.88|>": 51658,
947
+ "<|25.90|>": 51659,
948
+ "<|25.92|>": 51660,
949
+ "<|25.94|>": 51661,
950
+ "<|25.96|>": 51662,
951
+ "<|25.98|>": 51663,
952
+ "<|26.00|>": 51664,
953
+ "<|26.02|>": 51665,
954
+ "<|26.04|>": 51666,
955
+ "<|26.06|>": 51667,
956
+ "<|26.08|>": 51668,
957
+ "<|26.10|>": 51669,
958
+ "<|26.12|>": 51670,
959
+ "<|26.14|>": 51671,
960
+ "<|26.16|>": 51672,
961
+ "<|26.18|>": 51673,
962
+ "<|26.20|>": 51674,
963
+ "<|26.22|>": 51675,
964
+ "<|26.24|>": 51676,
965
+ "<|26.26|>": 51677,
966
+ "<|26.28|>": 51678,
967
+ "<|26.30|>": 51679,
968
+ "<|26.32|>": 51680,
969
+ "<|26.34|>": 51681,
970
+ "<|26.36|>": 51682,
971
+ "<|26.38|>": 51683,
972
+ "<|26.40|>": 51684,
973
+ "<|26.42|>": 51685,
974
+ "<|26.44|>": 51686,
975
+ "<|26.46|>": 51687,
976
+ "<|26.48|>": 51688,
977
+ "<|26.50|>": 51689,
978
+ "<|26.52|>": 51690,
979
+ "<|26.54|>": 51691,
980
+ "<|26.56|>": 51692,
981
+ "<|26.58|>": 51693,
982
+ "<|26.60|>": 51694,
983
+ "<|26.62|>": 51695,
984
+ "<|26.64|>": 51696,
985
+ "<|26.66|>": 51697,
986
+ "<|26.68|>": 51698,
987
+ "<|26.70|>": 51699,
988
+ "<|26.72|>": 51700,
989
+ "<|26.74|>": 51701,
990
+ "<|26.76|>": 51702,
991
+ "<|26.78|>": 51703,
992
+ "<|26.80|>": 51704,
993
+ "<|26.82|>": 51705,
994
+ "<|26.84|>": 51706,
995
+ "<|26.86|>": 51707,
996
+ "<|26.88|>": 51708,
997
+ "<|26.90|>": 51709,
998
+ "<|26.92|>": 51710,
999
+ "<|26.94|>": 51711,
1000
+ "<|26.96|>": 51712,
1001
+ "<|26.98|>": 51713,
1002
+ "<|27.00|>": 51714,
1003
+ "<|27.02|>": 51715,
1004
+ "<|27.04|>": 51716,
1005
+ "<|27.06|>": 51717,
1006
+ "<|27.08|>": 51718,
1007
+ "<|27.10|>": 51719,
1008
+ "<|27.12|>": 51720,
1009
+ "<|27.14|>": 51721,
1010
+ "<|27.16|>": 51722,
1011
+ "<|27.18|>": 51723,
1012
+ "<|27.20|>": 51724,
1013
+ "<|27.22|>": 51725,
1014
+ "<|27.24|>": 51726,
1015
+ "<|27.26|>": 51727,
1016
+ "<|27.28|>": 51728,
1017
+ "<|27.30|>": 51729,
1018
+ "<|27.32|>": 51730,
1019
+ "<|27.34|>": 51731,
1020
+ "<|27.36|>": 51732,
1021
+ "<|27.38|>": 51733,
1022
+ "<|27.40|>": 51734,
1023
+ "<|27.42|>": 51735,
1024
+ "<|27.44|>": 51736,
1025
+ "<|27.46|>": 51737,
1026
+ "<|27.48|>": 51738,
1027
+ "<|27.50|>": 51739,
1028
+ "<|27.52|>": 51740,
1029
+ "<|27.54|>": 51741,
1030
+ "<|27.56|>": 51742,
1031
+ "<|27.58|>": 51743,
1032
+ "<|27.60|>": 51744,
1033
+ "<|27.62|>": 51745,
1034
+ "<|27.64|>": 51746,
1035
+ "<|27.66|>": 51747,
1036
+ "<|27.68|>": 51748,
1037
+ "<|27.70|>": 51749,
1038
+ "<|27.72|>": 51750,
1039
+ "<|27.74|>": 51751,
1040
+ "<|27.76|>": 51752,
1041
+ "<|27.78|>": 51753,
1042
+ "<|27.80|>": 51754,
1043
+ "<|27.82|>": 51755,
1044
+ "<|27.84|>": 51756,
1045
+ "<|27.86|>": 51757,
1046
+ "<|27.88|>": 51758,
1047
+ "<|27.90|>": 51759,
1048
+ "<|27.92|>": 51760,
1049
+ "<|27.94|>": 51761,
1050
+ "<|27.96|>": 51762,
1051
+ "<|27.98|>": 51763,
1052
+ "<|28.00|>": 51764,
1053
+ "<|28.02|>": 51765,
1054
+ "<|28.04|>": 51766,
1055
+ "<|28.06|>": 51767,
1056
+ "<|28.08|>": 51768,
1057
+ "<|28.10|>": 51769,
1058
+ "<|28.12|>": 51770,
1059
+ "<|28.14|>": 51771,
1060
+ "<|28.16|>": 51772,
1061
+ "<|28.18|>": 51773,
1062
+ "<|28.20|>": 51774,
1063
+ "<|28.22|>": 51775,
1064
+ "<|28.24|>": 51776,
1065
+ "<|28.26|>": 51777,
1066
+ "<|28.28|>": 51778,
1067
+ "<|28.30|>": 51779,
1068
+ "<|28.32|>": 51780,
1069
+ "<|28.34|>": 51781,
1070
+ "<|28.36|>": 51782,
1071
+ "<|28.38|>": 51783,
1072
+ "<|28.40|>": 51784,
1073
+ "<|28.42|>": 51785,
1074
+ "<|28.44|>": 51786,
1075
+ "<|28.46|>": 51787,
1076
+ "<|28.48|>": 51788,
1077
+ "<|28.50|>": 51789,
1078
+ "<|28.52|>": 51790,
1079
+ "<|28.54|>": 51791,
1080
+ "<|28.56|>": 51792,
1081
+ "<|28.58|>": 51793,
1082
+ "<|28.60|>": 51794,
1083
+ "<|28.62|>": 51795,
1084
+ "<|28.64|>": 51796,
1085
+ "<|28.66|>": 51797,
1086
+ "<|28.68|>": 51798,
1087
+ "<|28.70|>": 51799,
1088
+ "<|28.72|>": 51800,
1089
+ "<|28.74|>": 51801,
1090
+ "<|28.76|>": 51802,
1091
+ "<|28.78|>": 51803,
1092
+ "<|28.80|>": 51804,
1093
+ "<|28.82|>": 51805,
1094
+ "<|28.84|>": 51806,
1095
+ "<|28.86|>": 51807,
1096
+ "<|28.88|>": 51808,
1097
+ "<|28.90|>": 51809,
1098
+ "<|28.92|>": 51810,
1099
+ "<|28.94|>": 51811,
1100
+ "<|28.96|>": 51812,
1101
+ "<|28.98|>": 51813,
1102
+ "<|29.00|>": 51814,
1103
+ "<|29.02|>": 51815,
1104
+ "<|29.04|>": 51816,
1105
+ "<|29.06|>": 51817,
1106
+ "<|29.08|>": 51818,
1107
+ "<|29.10|>": 51819,
1108
+ "<|29.12|>": 51820,
1109
+ "<|29.14|>": 51821,
1110
+ "<|29.16|>": 51822,
1111
+ "<|29.18|>": 51823,
1112
+ "<|29.20|>": 51824,
1113
+ "<|29.22|>": 51825,
1114
+ "<|29.24|>": 51826,
1115
+ "<|29.26|>": 51827,
1116
+ "<|29.28|>": 51828,
1117
+ "<|29.30|>": 51829,
1118
+ "<|29.32|>": 51830,
1119
+ "<|29.34|>": 51831,
1120
+ "<|29.36|>": 51832,
1121
+ "<|29.38|>": 51833,
1122
+ "<|29.40|>": 51834,
1123
+ "<|29.42|>": 51835,
1124
+ "<|29.44|>": 51836,
1125
+ "<|29.46|>": 51837,
1126
+ "<|29.48|>": 51838,
1127
+ "<|29.50|>": 51839,
1128
+ "<|29.52|>": 51840,
1129
+ "<|29.54|>": 51841,
1130
+ "<|29.56|>": 51842,
1131
+ "<|29.58|>": 51843,
1132
+ "<|29.60|>": 51844,
1133
+ "<|29.62|>": 51845,
1134
+ "<|29.64|>": 51846,
1135
+ "<|29.66|>": 51847,
1136
+ "<|29.68|>": 51848,
1137
+ "<|29.70|>": 51849,
1138
+ "<|29.72|>": 51850,
1139
+ "<|29.74|>": 51851,
1140
+ "<|29.76|>": 51852,
1141
+ "<|29.78|>": 51853,
1142
+ "<|29.80|>": 51854,
1143
+ "<|29.82|>": 51855,
1144
+ "<|29.84|>": 51856,
1145
+ "<|29.86|>": 51857,
1146
+ "<|29.88|>": 51858,
1147
+ "<|29.90|>": 51859,
1148
+ "<|29.92|>": 51860,
1149
+ "<|29.94|>": 51861,
1150
+ "<|29.96|>": 51862,
1151
+ "<|29.98|>": 51863,
1152
+ "<|3.00|>": 50514,
1153
+ "<|3.02|>": 50515,
1154
+ "<|3.04|>": 50516,
1155
+ "<|3.06|>": 50517,
1156
+ "<|3.08|>": 50518,
1157
+ "<|3.10|>": 50519,
1158
+ "<|3.12|>": 50520,
1159
+ "<|3.14|>": 50521,
1160
+ "<|3.16|>": 50522,
1161
+ "<|3.18|>": 50523,
1162
+ "<|3.20|>": 50524,
1163
+ "<|3.22|>": 50525,
1164
+ "<|3.24|>": 50526,
1165
+ "<|3.26|>": 50527,
1166
+ "<|3.28|>": 50528,
1167
+ "<|3.30|>": 50529,
1168
+ "<|3.32|>": 50530,
1169
+ "<|3.34|>": 50531,
1170
+ "<|3.36|>": 50532,
1171
+ "<|3.38|>": 50533,
1172
+ "<|3.40|>": 50534,
1173
+ "<|3.42|>": 50535,
1174
+ "<|3.44|>": 50536,
1175
+ "<|3.46|>": 50537,
1176
+ "<|3.48|>": 50538,
1177
+ "<|3.50|>": 50539,
1178
+ "<|3.52|>": 50540,
1179
+ "<|3.54|>": 50541,
1180
+ "<|3.56|>": 50542,
1181
+ "<|3.58|>": 50543,
1182
+ "<|3.60|>": 50544,
1183
+ "<|3.62|>": 50545,
1184
+ "<|3.64|>": 50546,
1185
+ "<|3.66|>": 50547,
1186
+ "<|3.68|>": 50548,
1187
+ "<|3.70|>": 50549,
1188
+ "<|3.72|>": 50550,
1189
+ "<|3.74|>": 50551,
1190
+ "<|3.76|>": 50552,
1191
+ "<|3.78|>": 50553,
1192
+ "<|3.80|>": 50554,
1193
+ "<|3.82|>": 50555,
1194
+ "<|3.84|>": 50556,
1195
+ "<|3.86|>": 50557,
1196
+ "<|3.88|>": 50558,
1197
+ "<|3.90|>": 50559,
1198
+ "<|3.92|>": 50560,
1199
+ "<|3.94|>": 50561,
1200
+ "<|3.96|>": 50562,
1201
+ "<|3.98|>": 50563,
1202
+ "<|30.00|>": 51864,
1203
+ "<|4.00|>": 50564,
1204
+ "<|4.02|>": 50565,
1205
+ "<|4.04|>": 50566,
1206
+ "<|4.06|>": 50567,
1207
+ "<|4.08|>": 50568,
1208
+ "<|4.10|>": 50569,
1209
+ "<|4.12|>": 50570,
1210
+ "<|4.14|>": 50571,
1211
+ "<|4.16|>": 50572,
1212
+ "<|4.18|>": 50573,
1213
+ "<|4.20|>": 50574,
1214
+ "<|4.22|>": 50575,
1215
+ "<|4.24|>": 50576,
1216
+ "<|4.26|>": 50577,
1217
+ "<|4.28|>": 50578,
1218
+ "<|4.30|>": 50579,
1219
+ "<|4.32|>": 50580,
1220
+ "<|4.34|>": 50581,
1221
+ "<|4.36|>": 50582,
1222
+ "<|4.38|>": 50583,
1223
+ "<|4.40|>": 50584,
1224
+ "<|4.42|>": 50585,
1225
+ "<|4.44|>": 50586,
1226
+ "<|4.46|>": 50587,
1227
+ "<|4.48|>": 50588,
1228
+ "<|4.50|>": 50589,
1229
+ "<|4.52|>": 50590,
1230
+ "<|4.54|>": 50591,
1231
+ "<|4.56|>": 50592,
1232
+ "<|4.58|>": 50593,
1233
+ "<|4.60|>": 50594,
1234
+ "<|4.62|>": 50595,
1235
+ "<|4.64|>": 50596,
1236
+ "<|4.66|>": 50597,
1237
+ "<|4.68|>": 50598,
1238
+ "<|4.70|>": 50599,
1239
+ "<|4.72|>": 50600,
1240
+ "<|4.74|>": 50601,
1241
+ "<|4.76|>": 50602,
1242
+ "<|4.78|>": 50603,
1243
+ "<|4.80|>": 50604,
1244
+ "<|4.82|>": 50605,
1245
+ "<|4.84|>": 50606,
1246
+ "<|4.86|>": 50607,
1247
+ "<|4.88|>": 50608,
1248
+ "<|4.90|>": 50609,
1249
+ "<|4.92|>": 50610,
1250
+ "<|4.94|>": 50611,
1251
+ "<|4.96|>": 50612,
1252
+ "<|4.98|>": 50613,
1253
+ "<|5.00|>": 50614,
1254
+ "<|5.02|>": 50615,
1255
+ "<|5.04|>": 50616,
1256
+ "<|5.06|>": 50617,
1257
+ "<|5.08|>": 50618,
1258
+ "<|5.10|>": 50619,
1259
+ "<|5.12|>": 50620,
1260
+ "<|5.14|>": 50621,
1261
+ "<|5.16|>": 50622,
1262
+ "<|5.18|>": 50623,
1263
+ "<|5.20|>": 50624,
1264
+ "<|5.22|>": 50625,
1265
+ "<|5.24|>": 50626,
1266
+ "<|5.26|>": 50627,
1267
+ "<|5.28|>": 50628,
1268
+ "<|5.30|>": 50629,
1269
+ "<|5.32|>": 50630,
1270
+ "<|5.34|>": 50631,
1271
+ "<|5.36|>": 50632,
1272
+ "<|5.38|>": 50633,
1273
+ "<|5.40|>": 50634,
1274
+ "<|5.42|>": 50635,
1275
+ "<|5.44|>": 50636,
1276
+ "<|5.46|>": 50637,
1277
+ "<|5.48|>": 50638,
1278
+ "<|5.50|>": 50639,
1279
+ "<|5.52|>": 50640,
1280
+ "<|5.54|>": 50641,
1281
+ "<|5.56|>": 50642,
1282
+ "<|5.58|>": 50643,
1283
+ "<|5.60|>": 50644,
1284
+ "<|5.62|>": 50645,
1285
+ "<|5.64|>": 50646,
1286
+ "<|5.66|>": 50647,
1287
+ "<|5.68|>": 50648,
1288
+ "<|5.70|>": 50649,
1289
+ "<|5.72|>": 50650,
1290
+ "<|5.74|>": 50651,
1291
+ "<|5.76|>": 50652,
1292
+ "<|5.78|>": 50653,
1293
+ "<|5.80|>": 50654,
1294
+ "<|5.82|>": 50655,
1295
+ "<|5.84|>": 50656,
1296
+ "<|5.86|>": 50657,
1297
+ "<|5.88|>": 50658,
1298
+ "<|5.90|>": 50659,
1299
+ "<|5.92|>": 50660,
1300
+ "<|5.94|>": 50661,
1301
+ "<|5.96|>": 50662,
1302
+ "<|5.98|>": 50663,
1303
+ "<|6.00|>": 50664,
1304
+ "<|6.02|>": 50665,
1305
+ "<|6.04|>": 50666,
1306
+ "<|6.06|>": 50667,
1307
+ "<|6.08|>": 50668,
1308
+ "<|6.10|>": 50669,
1309
+ "<|6.12|>": 50670,
1310
+ "<|6.14|>": 50671,
1311
+ "<|6.16|>": 50672,
1312
+ "<|6.18|>": 50673,
1313
+ "<|6.20|>": 50674,
1314
+ "<|6.22|>": 50675,
1315
+ "<|6.24|>": 50676,
1316
+ "<|6.26|>": 50677,
1317
+ "<|6.28|>": 50678,
1318
+ "<|6.30|>": 50679,
1319
+ "<|6.32|>": 50680,
1320
+ "<|6.34|>": 50681,
1321
+ "<|6.36|>": 50682,
1322
+ "<|6.38|>": 50683,
1323
+ "<|6.40|>": 50684,
1324
+ "<|6.42|>": 50685,
1325
+ "<|6.44|>": 50686,
1326
+ "<|6.46|>": 50687,
1327
+ "<|6.48|>": 50688,
1328
+ "<|6.50|>": 50689,
1329
+ "<|6.52|>": 50690,
1330
+ "<|6.54|>": 50691,
1331
+ "<|6.56|>": 50692,
1332
+ "<|6.58|>": 50693,
1333
+ "<|6.60|>": 50694,
1334
+ "<|6.62|>": 50695,
1335
+ "<|6.64|>": 50696,
1336
+ "<|6.66|>": 50697,
1337
+ "<|6.68|>": 50698,
1338
+ "<|6.70|>": 50699,
1339
+ "<|6.72|>": 50700,
1340
+ "<|6.74|>": 50701,
1341
+ "<|6.76|>": 50702,
1342
+ "<|6.78|>": 50703,
1343
+ "<|6.80|>": 50704,
1344
+ "<|6.82|>": 50705,
1345
+ "<|6.84|>": 50706,
1346
+ "<|6.86|>": 50707,
1347
+ "<|6.88|>": 50708,
1348
+ "<|6.90|>": 50709,
1349
+ "<|6.92|>": 50710,
1350
+ "<|6.94|>": 50711,
1351
+ "<|6.96|>": 50712,
1352
+ "<|6.98|>": 50713,
1353
+ "<|7.00|>": 50714,
1354
+ "<|7.02|>": 50715,
1355
+ "<|7.04|>": 50716,
1356
+ "<|7.06|>": 50717,
1357
+ "<|7.08|>": 50718,
1358
+ "<|7.10|>": 50719,
1359
+ "<|7.12|>": 50720,
1360
+ "<|7.14|>": 50721,
1361
+ "<|7.16|>": 50722,
1362
+ "<|7.18|>": 50723,
1363
+ "<|7.20|>": 50724,
1364
+ "<|7.22|>": 50725,
1365
+ "<|7.24|>": 50726,
1366
+ "<|7.26|>": 50727,
1367
+ "<|7.28|>": 50728,
1368
+ "<|7.30|>": 50729,
1369
+ "<|7.32|>": 50730,
1370
+ "<|7.34|>": 50731,
1371
+ "<|7.36|>": 50732,
1372
+ "<|7.38|>": 50733,
1373
+ "<|7.40|>": 50734,
1374
+ "<|7.42|>": 50735,
1375
+ "<|7.44|>": 50736,
1376
+ "<|7.46|>": 50737,
1377
+ "<|7.48|>": 50738,
1378
+ "<|7.50|>": 50739,
1379
+ "<|7.52|>": 50740,
1380
+ "<|7.54|>": 50741,
1381
+ "<|7.56|>": 50742,
1382
+ "<|7.58|>": 50743,
1383
+ "<|7.60|>": 50744,
1384
+ "<|7.62|>": 50745,
1385
+ "<|7.64|>": 50746,
1386
+ "<|7.66|>": 50747,
1387
+ "<|7.68|>": 50748,
1388
+ "<|7.70|>": 50749,
1389
+ "<|7.72|>": 50750,
1390
+ "<|7.74|>": 50751,
1391
+ "<|7.76|>": 50752,
1392
+ "<|7.78|>": 50753,
1393
+ "<|7.80|>": 50754,
1394
+ "<|7.82|>": 50755,
1395
+ "<|7.84|>": 50756,
1396
+ "<|7.86|>": 50757,
1397
+ "<|7.88|>": 50758,
1398
+ "<|7.90|>": 50759,
1399
+ "<|7.92|>": 50760,
1400
+ "<|7.94|>": 50761,
1401
+ "<|7.96|>": 50762,
1402
+ "<|7.98|>": 50763,
1403
+ "<|8.00|>": 50764,
1404
+ "<|8.02|>": 50765,
1405
+ "<|8.04|>": 50766,
1406
+ "<|8.06|>": 50767,
1407
+ "<|8.08|>": 50768,
1408
+ "<|8.10|>": 50769,
1409
+ "<|8.12|>": 50770,
1410
+ "<|8.14|>": 50771,
1411
+ "<|8.16|>": 50772,
1412
+ "<|8.18|>": 50773,
1413
+ "<|8.20|>": 50774,
1414
+ "<|8.22|>": 50775,
1415
+ "<|8.24|>": 50776,
1416
+ "<|8.26|>": 50777,
1417
+ "<|8.28|>": 50778,
1418
+ "<|8.30|>": 50779,
1419
+ "<|8.32|>": 50780,
1420
+ "<|8.34|>": 50781,
1421
+ "<|8.36|>": 50782,
1422
+ "<|8.38|>": 50783,
1423
+ "<|8.40|>": 50784,
1424
+ "<|8.42|>": 50785,
1425
+ "<|8.44|>": 50786,
1426
+ "<|8.46|>": 50787,
1427
+ "<|8.48|>": 50788,
1428
+ "<|8.50|>": 50789,
1429
+ "<|8.52|>": 50790,
1430
+ "<|8.54|>": 50791,
1431
+ "<|8.56|>": 50792,
1432
+ "<|8.58|>": 50793,
1433
+ "<|8.60|>": 50794,
1434
+ "<|8.62|>": 50795,
1435
+ "<|8.64|>": 50796,
1436
+ "<|8.66|>": 50797,
1437
+ "<|8.68|>": 50798,
1438
+ "<|8.70|>": 50799,
1439
+ "<|8.72|>": 50800,
1440
+ "<|8.74|>": 50801,
1441
+ "<|8.76|>": 50802,
1442
+ "<|8.78|>": 50803,
1443
+ "<|8.80|>": 50804,
1444
+ "<|8.82|>": 50805,
1445
+ "<|8.84|>": 50806,
1446
+ "<|8.86|>": 50807,
1447
+ "<|8.88|>": 50808,
1448
+ "<|8.90|>": 50809,
1449
+ "<|8.92|>": 50810,
1450
+ "<|8.94|>": 50811,
1451
+ "<|8.96|>": 50812,
1452
+ "<|8.98|>": 50813,
1453
+ "<|9.00|>": 50814,
1454
+ "<|9.02|>": 50815,
1455
+ "<|9.04|>": 50816,
1456
+ "<|9.06|>": 50817,
1457
+ "<|9.08|>": 50818,
1458
+ "<|9.10|>": 50819,
1459
+ "<|9.12|>": 50820,
1460
+ "<|9.14|>": 50821,
1461
+ "<|9.16|>": 50822,
1462
+ "<|9.18|>": 50823,
1463
+ "<|9.20|>": 50824,
1464
+ "<|9.22|>": 50825,
1465
+ "<|9.24|>": 50826,
1466
+ "<|9.26|>": 50827,
1467
+ "<|9.28|>": 50828,
1468
+ "<|9.30|>": 50829,
1469
+ "<|9.32|>": 50830,
1470
+ "<|9.34|>": 50831,
1471
+ "<|9.36|>": 50832,
1472
+ "<|9.38|>": 50833,
1473
+ "<|9.40|>": 50834,
1474
+ "<|9.42|>": 50835,
1475
+ "<|9.44|>": 50836,
1476
+ "<|9.46|>": 50837,
1477
+ "<|9.48|>": 50838,
1478
+ "<|9.50|>": 50839,
1479
+ "<|9.52|>": 50840,
1480
+ "<|9.54|>": 50841,
1481
+ "<|9.56|>": 50842,
1482
+ "<|9.58|>": 50843,
1483
+ "<|9.60|>": 50844,
1484
+ "<|9.62|>": 50845,
1485
+ "<|9.64|>": 50846,
1486
+ "<|9.66|>": 50847,
1487
+ "<|9.68|>": 50848,
1488
+ "<|9.70|>": 50849,
1489
+ "<|9.72|>": 50850,
1490
+ "<|9.74|>": 50851,
1491
+ "<|9.76|>": 50852,
1492
+ "<|9.78|>": 50853,
1493
+ "<|9.80|>": 50854,
1494
+ "<|9.82|>": 50855,
1495
+ "<|9.84|>": 50856,
1496
+ "<|9.86|>": 50857,
1497
+ "<|9.88|>": 50858,
1498
+ "<|9.90|>": 50859,
1499
+ "<|9.92|>": 50860,
1500
+ "<|9.94|>": 50861,
1501
+ "<|9.96|>": 50862,
1502
+ "<|9.98|>": 50863,
1503
+ "<|af|>": 50327,
1504
+ "<|am|>": 50334,
1505
+ "<|ar|>": 50272,
1506
+ "<|as|>": 50350,
1507
+ "<|az|>": 50304,
1508
+ "<|ba|>": 50355,
1509
+ "<|be|>": 50330,
1510
+ "<|bg|>": 50292,
1511
+ "<|bn|>": 50302,
1512
+ "<|bo|>": 50347,
1513
+ "<|br|>": 50309,
1514
+ "<|bs|>": 50315,
1515
+ "<|ca|>": 50270,
1516
+ "<|cs|>": 50283,
1517
+ "<|cy|>": 50297,
1518
+ "<|da|>": 50285,
1519
+ "<|de|>": 50261,
1520
+ "<|el|>": 50281,
1521
+ "<|en|>": 50259,
1522
+ "<|es|>": 50262,
1523
+ "<|et|>": 50307,
1524
+ "<|eu|>": 50310,
1525
+ "<|fa|>": 50300,
1526
+ "<|fi|>": 50277,
1527
+ "<|fo|>": 50338,
1528
+ "<|fr|>": 50265,
1529
+ "<|gl|>": 50319,
1530
+ "<|gu|>": 50333,
1531
+ "<|haw|>": 50352,
1532
+ "<|ha|>": 50354,
1533
+ "<|he|>": 50279,
1534
+ "<|hi|>": 50276,
1535
+ "<|hr|>": 50291,
1536
+ "<|ht|>": 50339,
1537
+ "<|hu|>": 50286,
1538
+ "<|hy|>": 50312,
1539
+ "<|id|>": 50275,
1540
+ "<|is|>": 50311,
1541
+ "<|it|>": 50274,
1542
+ "<|ja|>": 50266,
1543
+ "<|jw|>": 50356,
1544
+ "<|ka|>": 50329,
1545
+ "<|kk|>": 50316,
1546
+ "<|km|>": 50323,
1547
+ "<|kn|>": 50306,
1548
+ "<|ko|>": 50264,
1549
+ "<|la|>": 50294,
1550
+ "<|lb|>": 50345,
1551
+ "<|ln|>": 50353,
1552
+ "<|lo|>": 50336,
1553
+ "<|lt|>": 50293,
1554
+ "<|lv|>": 50301,
1555
+ "<|mg|>": 50349,
1556
+ "<|mi|>": 50295,
1557
+ "<|mk|>": 50308,
1558
+ "<|ml|>": 50296,
1559
+ "<|mn|>": 50314,
1560
+ "<|mr|>": 50320,
1561
+ "<|ms|>": 50282,
1562
+ "<|mt|>": 50343,
1563
+ "<|my|>": 50346,
1564
+ "<|ne|>": 50313,
1565
+ "<|nl|>": 50271,
1566
+ "<|nn|>": 50342,
1567
+ "<|nocaptions|>": 50362,
1568
+ "<|notimestamps|>": 50363,
1569
+ "<|no|>": 50288,
1570
+ "<|oc|>": 50328,
1571
+ "<|pa|>": 50321,
1572
+ "<|pl|>": 50269,
1573
+ "<|ps|>": 50340,
1574
+ "<|pt|>": 50267,
1575
+ "<|ro|>": 50284,
1576
+ "<|ru|>": 50263,
1577
+ "<|sa|>": 50344,
1578
+ "<|sd|>": 50332,
1579
+ "<|si|>": 50322,
1580
+ "<|sk|>": 50298,
1581
+ "<|sl|>": 50305,
1582
+ "<|sn|>": 50324,
1583
+ "<|so|>": 50326,
1584
+ "<|sq|>": 50317,
1585
+ "<|sr|>": 50303,
1586
+ "<|startoflm|>": 50360,
1587
+ "<|startofprev|>": 50361,
1588
+ "<|startoftranscript|>": 50258,
1589
+ "<|su|>": 50357,
1590
+ "<|sv|>": 50273,
1591
+ "<|sw|>": 50318,
1592
+ "<|ta|>": 50287,
1593
+ "<|te|>": 50299,
1594
+ "<|tg|>": 50331,
1595
+ "<|th|>": 50289,
1596
+ "<|tk|>": 50341,
1597
+ "<|tl|>": 50348,
1598
+ "<|transcribe|>": 50359,
1599
+ "<|translate|>": 50358,
1600
+ "<|tr|>": 50268,
1601
+ "<|tt|>": 50351,
1602
+ "<|uk|>": 50280,
1603
+ "<|ur|>": 50290,
1604
+ "<|uz|>": 50337,
1605
+ "<|vi|>": 50278,
1606
+ "<|yi|>": 50335,
1607
+ "<|yo|>": 50325,
1608
+ "<|zh|>": 50260
1609
+ }
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.43,
3
+ "eval_loss": 0.267061322927475,
4
+ "eval_runtime": 1894.4312,
5
+ "eval_samples_per_second": 4.917,
6
+ "eval_steps_per_second": 0.154,
7
+ "eval_wer": 35.60262364321316,
8
+ "train_loss": 0.23807335948944092,
9
+ "train_runtime": 7036.0339,
10
+ "train_samples_per_second": 9.096,
11
+ "train_steps_per_second": 0.142
12
+ }
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "arun100/whisper-base-bn",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 512,
17
+ "decoder_attention_heads": 8,
18
+ "decoder_ffn_dim": 2048,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 6,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 8,
24
+ "encoder_ffn_dim": 2048,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": null,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
+ "max_length": 448,
38
+ "max_source_positions": 1500,
39
+ "max_target_positions": 448,
40
+ "median_filter_width": 7,
41
+ "model_type": "whisper",
42
+ "num_hidden_layers": 6,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50257,
45
+ "scale_embedding": false,
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.37.0.dev0",
48
+ "use_cache": false,
49
+ "use_weighted_layer_sum": false,
50
+ "vocab_size": 51865
51
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.43,
3
+ "eval_loss": 0.267061322927475,
4
+ "eval_runtime": 1894.4312,
5
+ "eval_samples_per_second": 4.917,
6
+ "eval_steps_per_second": 0.154,
7
+ "eval_wer": 35.60262364321316
8
+ }
generation_config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 3,
5
+ 1
6
+ ],
7
+ [
8
+ 4,
9
+ 2
10
+ ],
11
+ [
12
+ 4,
13
+ 3
14
+ ],
15
+ [
16
+ 4,
17
+ 7
18
+ ],
19
+ [
20
+ 5,
21
+ 1
22
+ ],
23
+ [
24
+ 5,
25
+ 2
26
+ ],
27
+ [
28
+ 5,
29
+ 4
30
+ ],
31
+ [
32
+ 5,
33
+ 6
34
+ ]
35
+ ],
36
+ "begin_suppress_tokens": [
37
+ 220,
38
+ 50257
39
+ ],
40
+ "bos_token_id": 50257,
41
+ "decoder_start_token_id": 50258,
42
+ "eos_token_id": 50257,
43
+ "forced_decoder_ids": [
44
+ [
45
+ 1,
46
+ null
47
+ ],
48
+ [
49
+ 2,
50
+ 50359
51
+ ]
52
+ ],
53
+ "is_multilingual": true,
54
+ "lang_to_id": {
55
+ "<|af|>": 50327,
56
+ "<|am|>": 50334,
57
+ "<|ar|>": 50272,
58
+ "<|as|>": 50350,
59
+ "<|az|>": 50304,
60
+ "<|ba|>": 50355,
61
+ "<|be|>": 50330,
62
+ "<|bg|>": 50292,
63
+ "<|bn|>": 50302,
64
+ "<|bo|>": 50347,
65
+ "<|br|>": 50309,
66
+ "<|bs|>": 50315,
67
+ "<|ca|>": 50270,
68
+ "<|cs|>": 50283,
69
+ "<|cy|>": 50297,
70
+ "<|da|>": 50285,
71
+ "<|de|>": 50261,
72
+ "<|el|>": 50281,
73
+ "<|en|>": 50259,
74
+ "<|es|>": 50262,
75
+ "<|et|>": 50307,
76
+ "<|eu|>": 50310,
77
+ "<|fa|>": 50300,
78
+ "<|fi|>": 50277,
79
+ "<|fo|>": 50338,
80
+ "<|fr|>": 50265,
81
+ "<|gl|>": 50319,
82
+ "<|gu|>": 50333,
83
+ "<|haw|>": 50352,
84
+ "<|ha|>": 50354,
85
+ "<|he|>": 50279,
86
+ "<|hi|>": 50276,
87
+ "<|hr|>": 50291,
88
+ "<|ht|>": 50339,
89
+ "<|hu|>": 50286,
90
+ "<|hy|>": 50312,
91
+ "<|id|>": 50275,
92
+ "<|is|>": 50311,
93
+ "<|it|>": 50274,
94
+ "<|ja|>": 50266,
95
+ "<|jw|>": 50356,
96
+ "<|ka|>": 50329,
97
+ "<|kk|>": 50316,
98
+ "<|km|>": 50323,
99
+ "<|kn|>": 50306,
100
+ "<|ko|>": 50264,
101
+ "<|la|>": 50294,
102
+ "<|lb|>": 50345,
103
+ "<|ln|>": 50353,
104
+ "<|lo|>": 50336,
105
+ "<|lt|>": 50293,
106
+ "<|lv|>": 50301,
107
+ "<|mg|>": 50349,
108
+ "<|mi|>": 50295,
109
+ "<|mk|>": 50308,
110
+ "<|ml|>": 50296,
111
+ "<|mn|>": 50314,
112
+ "<|mr|>": 50320,
113
+ "<|ms|>": 50282,
114
+ "<|mt|>": 50343,
115
+ "<|my|>": 50346,
116
+ "<|ne|>": 50313,
117
+ "<|nl|>": 50271,
118
+ "<|nn|>": 50342,
119
+ "<|no|>": 50288,
120
+ "<|oc|>": 50328,
121
+ "<|pa|>": 50321,
122
+ "<|pl|>": 50269,
123
+ "<|ps|>": 50340,
124
+ "<|pt|>": 50267,
125
+ "<|ro|>": 50284,
126
+ "<|ru|>": 50263,
127
+ "<|sa|>": 50344,
128
+ "<|sd|>": 50332,
129
+ "<|si|>": 50322,
130
+ "<|sk|>": 50298,
131
+ "<|sl|>": 50305,
132
+ "<|sn|>": 50324,
133
+ "<|so|>": 50326,
134
+ "<|sq|>": 50317,
135
+ "<|sr|>": 50303,
136
+ "<|su|>": 50357,
137
+ "<|sv|>": 50273,
138
+ "<|sw|>": 50318,
139
+ "<|ta|>": 50287,
140
+ "<|te|>": 50299,
141
+ "<|tg|>": 50331,
142
+ "<|th|>": 50289,
143
+ "<|tk|>": 50341,
144
+ "<|tl|>": 50348,
145
+ "<|tr|>": 50268,
146
+ "<|tt|>": 50351,
147
+ "<|uk|>": 50280,
148
+ "<|ur|>": 50290,
149
+ "<|uz|>": 50337,
150
+ "<|vi|>": 50278,
151
+ "<|yi|>": 50335,
152
+ "<|yo|>": 50325,
153
+ "<|zh|>": 50260
154
+ },
155
+ "max_initial_timestamp_index": 1,
156
+ "max_length": 448,
157
+ "no_timestamps_token_id": 50363,
158
+ "pad_token_id": 50257,
159
+ "return_timestamps": false,
160
+ "suppress_tokens": [
161
+ 1,
162
+ 2,
163
+ 7,
164
+ 8,
165
+ 9,
166
+ 10,
167
+ 14,
168
+ 25,
169
+ 26,
170
+ 27,
171
+ 28,
172
+ 29,
173
+ 31,
174
+ 58,
175
+ 59,
176
+ 60,
177
+ 61,
178
+ 62,
179
+ 63,
180
+ 90,
181
+ 91,
182
+ 92,
183
+ 93,
184
+ 359,
185
+ 503,
186
+ 522,
187
+ 542,
188
+ 873,
189
+ 893,
190
+ 902,
191
+ 918,
192
+ 922,
193
+ 931,
194
+ 1350,
195
+ 1853,
196
+ 1982,
197
+ 2460,
198
+ 2627,
199
+ 3246,
200
+ 3253,
201
+ 3268,
202
+ 3536,
203
+ 3846,
204
+ 3961,
205
+ 4183,
206
+ 4667,
207
+ 6585,
208
+ 6647,
209
+ 7273,
210
+ 9061,
211
+ 9383,
212
+ 10428,
213
+ 10929,
214
+ 11938,
215
+ 12033,
216
+ 12331,
217
+ 12562,
218
+ 13793,
219
+ 14157,
220
+ 14635,
221
+ 15265,
222
+ 15618,
223
+ 16553,
224
+ 16604,
225
+ 18362,
226
+ 18956,
227
+ 20075,
228
+ 21675,
229
+ 22520,
230
+ 26130,
231
+ 26161,
232
+ 26435,
233
+ 28279,
234
+ 29464,
235
+ 31650,
236
+ 32302,
237
+ 32470,
238
+ 36865,
239
+ 42863,
240
+ 47425,
241
+ 49870,
242
+ 50254,
243
+ 50258,
244
+ 50358,
245
+ 50359,
246
+ 50360,
247
+ 50361,
248
+ 50362
249
+ ],
250
+ "task_to_id": {
251
+ "transcribe": 50359,
252
+ "translate": 50358
253
+ },
254
+ "transformers_version": "4.37.0.dev0"
255
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2777c183b455d0559dde155a266d3d5b9f6377f6127991e4864330792ebd3910
3
+ size 290403936
normalizer.json ADDED
@@ -0,0 +1,1742 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "accessorise": "accessorize",
3
+ "accessorised": "accessorized",
4
+ "accessorises": "accessorizes",
5
+ "accessorising": "accessorizing",
6
+ "acclimatisation": "acclimatization",
7
+ "acclimatise": "acclimatize",
8
+ "acclimatised": "acclimatized",
9
+ "acclimatises": "acclimatizes",
10
+ "acclimatising": "acclimatizing",
11
+ "accoutrements": "accouterments",
12
+ "aeon": "eon",
13
+ "aeons": "eons",
14
+ "aerogramme": "aerogram",
15
+ "aerogrammes": "aerograms",
16
+ "aeroplane": "airplane",
17
+ "aeroplanes": "airplanes",
18
+ "aesthete": "esthete",
19
+ "aesthetes": "esthetes",
20
+ "aesthetic": "esthetic",
21
+ "aesthetically": "esthetically",
22
+ "aesthetics": "esthetics",
23
+ "aetiology": "etiology",
24
+ "ageing": "aging",
25
+ "aggrandisement": "aggrandizement",
26
+ "agonise": "agonize",
27
+ "agonised": "agonized",
28
+ "agonises": "agonizes",
29
+ "agonising": "agonizing",
30
+ "agonisingly": "agonizingly",
31
+ "almanack": "almanac",
32
+ "almanacks": "almanacs",
33
+ "aluminium": "aluminum",
34
+ "amortisable": "amortizable",
35
+ "amortisation": "amortization",
36
+ "amortisations": "amortizations",
37
+ "amortise": "amortize",
38
+ "amortised": "amortized",
39
+ "amortises": "amortizes",
40
+ "amortising": "amortizing",
41
+ "amphitheatre": "amphitheater",
42
+ "amphitheatres": "amphitheaters",
43
+ "anaemia": "anemia",
44
+ "anaemic": "anemic",
45
+ "anaesthesia": "anesthesia",
46
+ "anaesthetic": "anesthetic",
47
+ "anaesthetics": "anesthetics",
48
+ "anaesthetise": "anesthetize",
49
+ "anaesthetised": "anesthetized",
50
+ "anaesthetises": "anesthetizes",
51
+ "anaesthetising": "anesthetizing",
52
+ "anaesthetist": "anesthetist",
53
+ "anaesthetists": "anesthetists",
54
+ "anaesthetize": "anesthetize",
55
+ "anaesthetized": "anesthetized",
56
+ "anaesthetizes": "anesthetizes",
57
+ "anaesthetizing": "anesthetizing",
58
+ "analogue": "analog",
59
+ "analogues": "analogs",
60
+ "analyse": "analyze",
61
+ "analysed": "analyzed",
62
+ "analyses": "analyzes",
63
+ "analysing": "analyzing",
64
+ "anglicise": "anglicize",
65
+ "anglicised": "anglicized",
66
+ "anglicises": "anglicizes",
67
+ "anglicising": "anglicizing",
68
+ "annualised": "annualized",
69
+ "antagonise": "antagonize",
70
+ "antagonised": "antagonized",
71
+ "antagonises": "antagonizes",
72
+ "antagonising": "antagonizing",
73
+ "apologise": "apologize",
74
+ "apologised": "apologized",
75
+ "apologises": "apologizes",
76
+ "apologising": "apologizing",
77
+ "appal": "appall",
78
+ "appals": "appalls",
79
+ "appetiser": "appetizer",
80
+ "appetisers": "appetizers",
81
+ "appetising": "appetizing",
82
+ "appetisingly": "appetizingly",
83
+ "arbour": "arbor",
84
+ "arbours": "arbors",
85
+ "archaeologically": "archeologically",
86
+ "archaeologist": "archeologist",
87
+ "archaeologists": "archeologists",
88
+ "archaeology": "archeology</span>",
89
+ "archeological": "archaeological",
90
+ "ardour": "ardor",
91
+ "armour": "armor",
92
+ "armoured": "armored",
93
+ "armourer": "armorer",
94
+ "armourers": "armorers",
95
+ "armouries": "armories",
96
+ "armoury": "armory",
97
+ "artefact": "artifact",
98
+ "artefacts": "artifacts",
99
+ "authorise": "authorize",
100
+ "authorised": "authorized",
101
+ "authorises": "authorizes",
102
+ "authorising": "authorizing",
103
+ "axe": "ax",
104
+ "backpedalled": "backpedaled",
105
+ "backpedalling": "backpedaling",
106
+ "bannister": "banister",
107
+ "bannisters": "banisters",
108
+ "baptise": "baptize",
109
+ "baptised": "baptized",
110
+ "baptises": "baptizes",
111
+ "baptising": "baptizing",
112
+ "bastardise": "bastardize",
113
+ "bastardised": "bastardized",
114
+ "bastardises": "bastardizes",
115
+ "bastardising": "bastardizing",
116
+ "battleax": "battleaxe",
117
+ "baulk": "balk",
118
+ "baulked": "balked",
119
+ "baulking": "balking",
120
+ "baulks": "balks",
121
+ "bedevilled": "bedeviled",
122
+ "bedevilling": "bedeviling",
123
+ "behaviour": "behavior",
124
+ "behavioural": "behavioral",
125
+ "behaviourism": "behaviorism",
126
+ "behaviourist": "behaviorist",
127
+ "behaviourists": "behaviorists",
128
+ "behaviours": "behaviors",
129
+ "behove": "behoove",
130
+ "behoved": "behooved",
131
+ "behoves": "behooves",
132
+ "bejewelled": "bejeweled",
133
+ "belabour": "belabor",
134
+ "belaboured": "belabored",
135
+ "belabouring": "belaboring",
136
+ "belabours": "belabors",
137
+ "bevelled": "beveled",
138
+ "bevvies": "bevies",
139
+ "bevvy": "bevy",
140
+ "biassed": "biased",
141
+ "biassing": "biasing",
142
+ "bingeing": "binging",
143
+ "bougainvillaea": "bougainvillea",
144
+ "bougainvillaeas": "bougainvilleas",
145
+ "bowdlerise": "bowdlerize",
146
+ "bowdlerised": "bowdlerized",
147
+ "bowdlerises": "bowdlerizes",
148
+ "bowdlerising": "bowdlerizing",
149
+ "breathalyse": "breathalyze",
150
+ "breathalysed": "breathalyzed",
151
+ "breathalyser": "breathalyzer",
152
+ "breathalysers": "breathalyzers",
153
+ "breathalyses": "breathalyzes",
154
+ "breathalysing": "breathalyzing",
155
+ "brutalise": "brutalize",
156
+ "brutalised": "brutalized",
157
+ "brutalises": "brutalizes",
158
+ "brutalising": "brutalizing",
159
+ "busses": "buses",
160
+ "bussing": "busing",
161
+ "caesarean": "cesarean",
162
+ "caesareans": "cesareans",
163
+ "calibre": "caliber",
164
+ "calibres": "calibers",
165
+ "calliper": "caliper",
166
+ "callipers": "calipers",
167
+ "callisthenics": "calisthenics",
168
+ "canalise": "canalize",
169
+ "canalised": "canalized",
170
+ "canalises": "canalizes",
171
+ "canalising": "canalizing",
172
+ "cancelation": "cancellation",
173
+ "cancelations": "cancellations",
174
+ "cancelled": "canceled",
175
+ "cancelling": "canceling",
176
+ "candour": "candor",
177
+ "cannibalise": "cannibalize",
178
+ "cannibalised": "cannibalized",
179
+ "cannibalises": "cannibalizes",
180
+ "cannibalising": "cannibalizing",
181
+ "canonise": "canonize",
182
+ "canonised": "canonized",
183
+ "canonises": "canonizes",
184
+ "canonising": "canonizing",
185
+ "capitalise": "capitalize",
186
+ "capitalised": "capitalized",
187
+ "capitalises": "capitalizes",
188
+ "capitalising": "capitalizing",
189
+ "caramelise": "caramelize",
190
+ "caramelised": "caramelized",
191
+ "caramelises": "caramelizes",
192
+ "caramelising": "caramelizing",
193
+ "carbonise": "carbonize",
194
+ "carbonised": "carbonized",
195
+ "carbonises": "carbonizes",
196
+ "carbonising": "carbonizing",
197
+ "carolled": "caroled",
198
+ "carolling": "caroling",
199
+ "catalogue": "catalog",
200
+ "catalogued": "cataloged",
201
+ "catalogues": "catalogs",
202
+ "cataloguing": "cataloging",
203
+ "catalyse": "catalyze",
204
+ "catalysed": "catalyzed",
205
+ "catalyses": "catalyzes",
206
+ "catalysing": "catalyzing",
207
+ "categorise": "categorize",
208
+ "categorised": "categorized",
209
+ "categorises": "categorizes",
210
+ "categorising": "categorizing",
211
+ "cauterise": "cauterize",
212
+ "cauterised": "cauterized",
213
+ "cauterises": "cauterizes",
214
+ "cauterising": "cauterizing",
215
+ "cavilled": "caviled",
216
+ "cavilling": "caviling",
217
+ "centigramme": "centigram",
218
+ "centigrammes": "centigrams",
219
+ "centilitre": "centiliter",
220
+ "centilitres": "centiliters",
221
+ "centimetre": "centimeter",
222
+ "centimetres": "centimeters",
223
+ "centralise": "centralize",
224
+ "centralised": "centralized",
225
+ "centralises": "centralizes",
226
+ "centralising": "centralizing",
227
+ "centre": "center",
228
+ "centred": "centered",
229
+ "centrefold": "centerfold",
230
+ "centrefolds": "centerfolds",
231
+ "centrepiece": "centerpiece",
232
+ "centrepieces": "centerpieces",
233
+ "centres": "centers",
234
+ "channelled": "channeled",
235
+ "channelling": "channeling",
236
+ "characterise": "characterize",
237
+ "characterised": "characterized",
238
+ "characterises": "characterizes",
239
+ "characterising": "characterizing",
240
+ "cheque": "check",
241
+ "chequebook": "checkbook",
242
+ "chequebooks": "checkbooks",
243
+ "chequered": "checkered",
244
+ "cheques": "checks",
245
+ "chilli": "chili",
246
+ "chimaera": "chimera",
247
+ "chimaeras": "chimeras",
248
+ "chiselled": "chiseled",
249
+ "chiselling": "chiseling",
250
+ "circularise": "circularize",
251
+ "circularised": "circularized",
252
+ "circularises": "circularizes",
253
+ "circularising": "circularizing",
254
+ "civilise": "civilize",
255
+ "civilised": "civilized",
256
+ "civilises": "civilizes",
257
+ "civilising": "civilizing",
258
+ "clamour": "clamor",
259
+ "clamoured": "clamored",
260
+ "clamouring": "clamoring",
261
+ "clamours": "clamors",
262
+ "clangour": "clangor",
263
+ "clarinettist": "clarinetist",
264
+ "clarinettists": "clarinetists",
265
+ "collectivise": "collectivize",
266
+ "collectivised": "collectivized",
267
+ "collectivises": "collectivizes",
268
+ "collectivising": "collectivizing",
269
+ "colonisation": "colonization",
270
+ "colonise": "colonize",
271
+ "colonised": "colonized",
272
+ "coloniser": "colonizer",
273
+ "colonisers": "colonizers",
274
+ "colonises": "colonizes",
275
+ "colonising": "colonizing",
276
+ "colour": "color",
277
+ "colourant": "colorant",
278
+ "colourants": "colorants",
279
+ "coloured": "colored",
280
+ "coloureds": "coloreds",
281
+ "colourful": "colorful",
282
+ "colourfully": "colorfully",
283
+ "colouring": "coloring",
284
+ "colourize": "colorize",
285
+ "colourized": "colorized",
286
+ "colourizes": "colorizes",
287
+ "colourizing": "colorizing",
288
+ "colourless": "colorless",
289
+ "colours": "colors",
290
+ "commercialise": "commercialize",
291
+ "commercialised": "commercialized",
292
+ "commercialises": "commercializes",
293
+ "commercialising": "commercializing",
294
+ "compartmentalise": "compartmentalize",
295
+ "compartmentalised": "compartmentalized",
296
+ "compartmentalises": "compartmentalizes",
297
+ "compartmentalising": "compartmentalizing",
298
+ "computerise": "computerize",
299
+ "computerised": "computerized",
300
+ "computerises": "computerizes",
301
+ "computerising": "computerizing",
302
+ "conceptualise": "conceptualize",
303
+ "conceptualised": "conceptualized",
304
+ "conceptualises": "conceptualizes",
305
+ "conceptualising": "conceptualizing",
306
+ "connexion": "connection",
307
+ "connexions": "connections",
308
+ "contextualise": "contextualize",
309
+ "contextualised": "contextualized",
310
+ "contextualises": "contextualizes",
311
+ "contextualising": "contextualizing",
312
+ "cosier": "cozier",
313
+ "cosies": "cozies",
314
+ "cosiest": "coziest",
315
+ "cosily": "cozily",
316
+ "cosiness": "coziness",
317
+ "cosy": "cozy",
318
+ "councillor": "councilor",
319
+ "councillors": "councilors",
320
+ "counselled": "counseled",
321
+ "counselling": "counseling",
322
+ "counsellor": "counselor",
323
+ "counsellors": "counselors",
324
+ "crenelated": "crenellated",
325
+ "criminalise": "criminalize",
326
+ "criminalised": "criminalized",
327
+ "criminalises": "criminalizes",
328
+ "criminalising": "criminalizing",
329
+ "criticise": "criticize",
330
+ "criticised": "criticized",
331
+ "criticises": "criticizes",
332
+ "criticising": "criticizing",
333
+ "crueller": "crueler",
334
+ "cruellest": "cruelest",
335
+ "crystallisation": "crystallization",
336
+ "crystallise": "crystallize",
337
+ "crystallised": "crystallized",
338
+ "crystallises": "crystallizes",
339
+ "crystallising": "crystallizing",
340
+ "cudgelled": "cudgeled",
341
+ "cudgelling": "cudgeling",
342
+ "customise": "customize",
343
+ "customised": "customized",
344
+ "customises": "customizes",
345
+ "customising": "customizing",
346
+ "cypher": "cipher",
347
+ "cyphers": "ciphers",
348
+ "decentralisation": "decentralization",
349
+ "decentralise": "decentralize",
350
+ "decentralised": "decentralized",
351
+ "decentralises": "decentralizes",
352
+ "decentralising": "decentralizing",
353
+ "decriminalisation": "decriminalization",
354
+ "decriminalise": "decriminalize",
355
+ "decriminalised": "decriminalized",
356
+ "decriminalises": "decriminalizes",
357
+ "decriminalising": "decriminalizing",
358
+ "defence": "defense",
359
+ "defenceless": "defenseless",
360
+ "defences": "defenses",
361
+ "dehumanisation": "dehumanization",
362
+ "dehumanise": "dehumanize",
363
+ "dehumanised": "dehumanized",
364
+ "dehumanises": "dehumanizes",
365
+ "dehumanising": "dehumanizing",
366
+ "demeanour": "demeanor",
367
+ "demilitarisation": "demilitarization",
368
+ "demilitarise": "demilitarize",
369
+ "demilitarised": "demilitarized",
370
+ "demilitarises": "demilitarizes",
371
+ "demilitarising": "demilitarizing",
372
+ "demobilisation": "demobilization",
373
+ "demobilise": "demobilize",
374
+ "demobilised": "demobilized",
375
+ "demobilises": "demobilizes",
376
+ "demobilising": "demobilizing",
377
+ "democratisation": "democratization",
378
+ "democratise": "democratize",
379
+ "democratised": "democratized",
380
+ "democratises": "democratizes",
381
+ "democratising": "democratizing",
382
+ "demonise": "demonize",
383
+ "demonised": "demonized",
384
+ "demonises": "demonizes",
385
+ "demonising": "demonizing",
386
+ "demoralisation": "demoralization",
387
+ "demoralise": "demoralize",
388
+ "demoralised": "demoralized",
389
+ "demoralises": "demoralizes",
390
+ "demoralising": "demoralizing",
391
+ "denationalisation": "denationalization",
392
+ "denationalise": "denationalize",
393
+ "denationalised": "denationalized",
394
+ "denationalises": "denationalizes",
395
+ "denationalising": "denationalizing",
396
+ "deodorise": "deodorize",
397
+ "deodorised": "deodorized",
398
+ "deodorises": "deodorizes",
399
+ "deodorising": "deodorizing",
400
+ "depersonalise": "depersonalize",
401
+ "depersonalised": "depersonalized",
402
+ "depersonalises": "depersonalizes",
403
+ "depersonalising": "depersonalizing",
404
+ "deputise": "deputize",
405
+ "deputised": "deputized",
406
+ "deputises": "deputizes",
407
+ "deputising": "deputizing",
408
+ "desensitisation": "desensitization",
409
+ "desensitise": "desensitize",
410
+ "desensitised": "desensitized",
411
+ "desensitises": "desensitizes",
412
+ "desensitising": "desensitizing",
413
+ "destabilisation": "destabilization",
414
+ "destabilise": "destabilize",
415
+ "destabilised": "destabilized",
416
+ "destabilises": "destabilizes",
417
+ "destabilising": "destabilizing",
418
+ "dialled": "dialed",
419
+ "dialling": "dialing",
420
+ "dialogue": "dialog",
421
+ "dialogues": "dialogs",
422
+ "diarrhoea": "diarrhea",
423
+ "digitise": "digitize",
424
+ "digitised": "digitized",
425
+ "digitises": "digitizes",
426
+ "digitising": "digitizing",
427
+ "disc": "disk",
428
+ "discolour": "discolor",
429
+ "discoloured": "discolored",
430
+ "discolouring": "discoloring",
431
+ "discolours": "discolors",
432
+ "discs": "disks",
433
+ "disembowelled": "disemboweled",
434
+ "disembowelling": "disemboweling",
435
+ "disfavour": "disfavor",
436
+ "dishevelled": "disheveled",
437
+ "dishonour": "dishonor",
438
+ "dishonourable": "dishonorable",
439
+ "dishonourably": "dishonorably",
440
+ "dishonoured": "dishonored",
441
+ "dishonouring": "dishonoring",
442
+ "dishonours": "dishonors",
443
+ "disorganisation": "disorganization",
444
+ "disorganised": "disorganized",
445
+ "distil": "distill",
446
+ "distils": "distills",
447
+ "dramatisation": "dramatization",
448
+ "dramatisations": "dramatizations",
449
+ "dramatise": "dramatize",
450
+ "dramatised": "dramatized",
451
+ "dramatises": "dramatizes",
452
+ "dramatising": "dramatizing",
453
+ "draught": "draft",
454
+ "draughtboard": "draftboard",
455
+ "draughtboards": "draftboards",
456
+ "draughtier": "draftier",
457
+ "draughtiest": "draftiest",
458
+ "draughts": "drafts",
459
+ "draughtsman": "draftsman",
460
+ "draughtsmanship": "draftsmanship",
461
+ "draughtsmen": "draftsmen",
462
+ "draughtswoman": "draftswoman",
463
+ "draughtswomen": "draftswomen",
464
+ "draughty": "drafty",
465
+ "drivelled": "driveled",
466
+ "drivelling": "driveling",
467
+ "duelled": "dueled",
468
+ "duelling": "dueling",
469
+ "economise": "economize",
470
+ "economised": "economized",
471
+ "economises": "economizes",
472
+ "economising": "economizing",
473
+ "editorialise": "editorialize",
474
+ "editorialised": "editorialized",
475
+ "editorialises": "editorializes",
476
+ "editorialising": "editorializing",
477
+ "edoema": "edema",
478
+ "empathise": "empathize",
479
+ "empathised": "empathized",
480
+ "empathises": "empathizes",
481
+ "empathising": "empathizing",
482
+ "emphasise": "emphasize",
483
+ "emphasised": "emphasized",
484
+ "emphasises": "emphasizes",
485
+ "emphasising": "emphasizing",
486
+ "enamelled": "enameled",
487
+ "enamelling": "enameling",
488
+ "enamoured": "enamored",
489
+ "encyclopaedia": "encyclopedia",
490
+ "encyclopaedias": "encyclopedias",
491
+ "encyclopaedic": "encyclopedic",
492
+ "endeavour": "endeavor",
493
+ "endeavoured": "endeavored",
494
+ "endeavouring": "endeavoring",
495
+ "endeavours": "endeavors",
496
+ "energise": "energize",
497
+ "energised": "energized",
498
+ "energises": "energizes",
499
+ "energising": "energizing",
500
+ "enrol": "enroll",
501
+ "enrols": "enrolls",
502
+ "enthral": "enthrall",
503
+ "enthrals": "enthralls",
504
+ "epaulette": "epaulet",
505
+ "epaulettes": "epaulets",
506
+ "epicentre": "epicenter",
507
+ "epicentres": "epicenters",
508
+ "epilogue": "epilog",
509
+ "epilogues": "epilogs",
510
+ "epitomise": "epitomize",
511
+ "epitomised": "epitomized",
512
+ "epitomises": "epitomizes",
513
+ "epitomising": "epitomizing",
514
+ "equalisation": "equalization",
515
+ "equalise": "equalize",
516
+ "equalised": "equalized",
517
+ "equaliser": "equalizer",
518
+ "equalisers": "equalizers",
519
+ "equalises": "equalizes",
520
+ "equalising": "equalizing",
521
+ "eulogise": "eulogize",
522
+ "eulogised": "eulogized",
523
+ "eulogises": "eulogizes",
524
+ "eulogising": "eulogizing",
525
+ "evangelise": "evangelize",
526
+ "evangelised": "evangelized",
527
+ "evangelises": "evangelizes",
528
+ "evangelising": "evangelizing",
529
+ "exorcise": "exorcize",
530
+ "exorcised": "exorcized",
531
+ "exorcises": "exorcizes",
532
+ "exorcising": "exorcizing",
533
+ "extemporisation": "extemporization",
534
+ "extemporise": "extemporize",
535
+ "extemporised": "extemporized",
536
+ "extemporises": "extemporizes",
537
+ "extemporising": "extemporizing",
538
+ "externalisation": "externalization",
539
+ "externalisations": "externalizations",
540
+ "externalise": "externalize",
541
+ "externalised": "externalized",
542
+ "externalises": "externalizes",
543
+ "externalising": "externalizing",
544
+ "factorise": "factorize",
545
+ "factorised": "factorized",
546
+ "factorises": "factorizes",
547
+ "factorising": "factorizing",
548
+ "faecal": "fecal",
549
+ "faeces": "feces",
550
+ "familiarisation": "familiarization",
551
+ "familiarise": "familiarize",
552
+ "familiarised": "familiarized",
553
+ "familiarises": "familiarizes",
554
+ "familiarising": "familiarizing",
555
+ "fantasise": "fantasize",
556
+ "fantasised": "fantasized",
557
+ "fantasises": "fantasizes",
558
+ "fantasising": "fantasizing",
559
+ "favour": "favor",
560
+ "favourable": "favorable",
561
+ "favourably": "favorably",
562
+ "favoured": "favored",
563
+ "favouring": "favoring",
564
+ "favourite": "favorite",
565
+ "favourites": "favorites",
566
+ "favouritism": "favoritism",
567
+ "favours": "favors",
568
+ "feminise": "feminize",
569
+ "feminised": "feminized",
570
+ "feminises": "feminizes",
571
+ "feminising": "feminizing",
572
+ "fertilisation": "fertilization",
573
+ "fertilise": "fertilize",
574
+ "fertilised": "fertilized",
575
+ "fertiliser": "fertilizer",
576
+ "fertilisers": "fertilizers",
577
+ "fertilises": "fertilizes",
578
+ "fertilising": "fertilizing",
579
+ "fervour": "fervor",
580
+ "fibre": "fiber",
581
+ "fibreglass": "fiberglass",
582
+ "fibres": "fibers",
583
+ "fictionalisation": "fictionalization",
584
+ "fictionalisations": "fictionalizations",
585
+ "fictionalise": "fictionalize",
586
+ "fictionalised": "fictionalized",
587
+ "fictionalises": "fictionalizes",
588
+ "fictionalising": "fictionalizing",
589
+ "fillet": "filet",
590
+ "filleted": "fileted",
591
+ "filleting": "fileting",
592
+ "fillets": "filets",
593
+ "finalisation": "finalization",
594
+ "finalise": "finalize",
595
+ "finalised": "finalized",
596
+ "finalises": "finalizes",
597
+ "finalising": "finalizing",
598
+ "flautist": "flutist",
599
+ "flautists": "flutists",
600
+ "flavour": "flavor",
601
+ "flavoured": "flavored",
602
+ "flavouring": "flavoring",
603
+ "flavourings": "flavorings",
604
+ "flavourless": "flavorless",
605
+ "flavours": "flavors",
606
+ "flavoursome": "flavorsome",
607
+ "flyer / flier": "flier / flyer",
608
+ "foetal": "fetal",
609
+ "foetid": "fetid",
610
+ "foetus": "fetus",
611
+ "foetuses": "fetuses",
612
+ "formalisation": "formalization",
613
+ "formalise": "formalize",
614
+ "formalised": "formalized",
615
+ "formalises": "formalizes",
616
+ "formalising": "formalizing",
617
+ "fossilisation": "fossilization",
618
+ "fossilise": "fossilize",
619
+ "fossilised": "fossilized",
620
+ "fossilises": "fossilizes",
621
+ "fossilising": "fossilizing",
622
+ "fraternisation": "fraternization",
623
+ "fraternise": "fraternize",
624
+ "fraternised": "fraternized",
625
+ "fraternises": "fraternizes",
626
+ "fraternising": "fraternizing",
627
+ "fulfil": "fulfill",
628
+ "fulfilment": "fulfillment",
629
+ "fulfils": "fulfills",
630
+ "funnelled": "funneled",
631
+ "funnelling": "funneling",
632
+ "gage": "gauge",
633
+ "gaged": "gauged",
634
+ "gages": "gauges",
635
+ "gaging": "gauging",
636
+ "galvanise": "galvanize",
637
+ "galvanised": "galvanized",
638
+ "galvanises": "galvanizes",
639
+ "galvanising": "galvanizing",
640
+ "gambolled": "gamboled",
641
+ "gambolling": "gamboling",
642
+ "gaol": "jail",
643
+ "gaolbird": "jailbird",
644
+ "gaolbirds": "jailbirds",
645
+ "gaolbreak": "jailbreak",
646
+ "gaolbreaks": "jailbreaks",
647
+ "gaoled": "jailed",
648
+ "gaoler": "jailer",
649
+ "gaolers": "jailers",
650
+ "gaoling": "jailing",
651
+ "gaols": "jails",
652
+ "gasses": "gases",
653
+ "generalisation": "generalization",
654
+ "generalisations": "generalizations",
655
+ "generalise": "generalize",
656
+ "generalised": "generalized",
657
+ "generalises": "generalizes",
658
+ "generalising": "generalizing",
659
+ "ghettoise": "ghettoize",
660
+ "ghettoised": "ghettoized",
661
+ "ghettoises": "ghettoizes",
662
+ "ghettoising": "ghettoizing",
663
+ "gipsies": "gypsies",
664
+ "glamor": "glamour",
665
+ "glamorise": "glamorize",
666
+ "glamorised": "glamorized",
667
+ "glamorises": "glamorizes",
668
+ "glamorising": "glamorizing",
669
+ "globalisation": "globalization",
670
+ "globalise": "globalize",
671
+ "globalised": "globalized",
672
+ "globalises": "globalizes",
673
+ "globalising": "globalizing",
674
+ "glueing": "gluing",
675
+ "goitre": "goiter",
676
+ "goitres": "goiters",
677
+ "gonorrhoea": "gonorrhea",
678
+ "gramme": "gram",
679
+ "grammes": "grams",
680
+ "gravelled": "graveled",
681
+ "grey": "gray",
682
+ "greyed": "grayed",
683
+ "greying": "graying",
684
+ "greyish": "grayish",
685
+ "greyness": "grayness",
686
+ "greys": "grays",
687
+ "grovelled": "groveled",
688
+ "grovelling": "groveling",
689
+ "groyne": "groin",
690
+ "groynes": "groins",
691
+ "gruelling": "grueling",
692
+ "gruellingly": "gruelingly",
693
+ "gryphon": "griffin",
694
+ "gryphons": "griffins",
695
+ "gynaecological": "gynecological",
696
+ "gynaecologist": "gynecologist",
697
+ "gynaecologists": "gynecologists",
698
+ "gynaecology": "gynecology",
699
+ "haematological": "hematological",
700
+ "haematologist": "hematologist",
701
+ "haematologists": "hematologists",
702
+ "haematology": "hematology",
703
+ "haemoglobin": "hemoglobin",
704
+ "haemophilia": "hemophilia",
705
+ "haemophiliac": "hemophiliac",
706
+ "haemophiliacs": "hemophiliacs",
707
+ "haemorrhage": "hemorrhage",
708
+ "haemorrhaged": "hemorrhaged",
709
+ "haemorrhages": "hemorrhages",
710
+ "haemorrhaging": "hemorrhaging",
711
+ "haemorrhoids": "hemorrhoids",
712
+ "harbour": "harbor",
713
+ "harboured": "harbored",
714
+ "harbouring": "harboring",
715
+ "harbours": "harbors",
716
+ "harmonisation": "harmonization",
717
+ "harmonise": "harmonize",
718
+ "harmonised": "harmonized",
719
+ "harmonises": "harmonizes",
720
+ "harmonising": "harmonizing",
721
+ "homoeopath": "homeopath",
722
+ "homoeopathic": "homeopathic",
723
+ "homoeopaths": "homeopaths",
724
+ "homoeopathy": "homeopathy",
725
+ "homogenise": "homogenize",
726
+ "homogenised": "homogenized",
727
+ "homogenises": "homogenizes",
728
+ "homogenising": "homogenizing",
729
+ "honour": "honor",
730
+ "honourable": "honorable",
731
+ "honourably": "honorably",
732
+ "honoured": "honored",
733
+ "honouring": "honoring",
734
+ "honours": "honors",
735
+ "hospitalisation": "hospitalization",
736
+ "hospitalise": "hospitalize",
737
+ "hospitalised": "hospitalized",
738
+ "hospitalises": "hospitalizes",
739
+ "hospitalising": "hospitalizing",
740
+ "humanise": "humanize",
741
+ "humanised": "humanized",
742
+ "humanises": "humanizes",
743
+ "humanising": "humanizing",
744
+ "humour": "humor",
745
+ "humoured": "humored",
746
+ "humouring": "humoring",
747
+ "humourless": "humorless",
748
+ "humours": "humors",
749
+ "hybridise": "hybridize",
750
+ "hybridised": "hybridized",
751
+ "hybridises": "hybridizes",
752
+ "hybridising": "hybridizing",
753
+ "hypnotise": "hypnotize",
754
+ "hypnotised": "hypnotized",
755
+ "hypnotises": "hypnotizes",
756
+ "hypnotising": "hypnotizing",
757
+ "hypothesise": "hypothesize",
758
+ "hypothesised": "hypothesized",
759
+ "hypothesises": "hypothesizes",
760
+ "hypothesising": "hypothesizing",
761
+ "idealisation": "idealization",
762
+ "idealise": "idealize",
763
+ "idealised": "idealized",
764
+ "idealises": "idealizes",
765
+ "idealising": "idealizing",
766
+ "idolise": "idolize",
767
+ "idolised": "idolized",
768
+ "idolises": "idolizes",
769
+ "idolising": "idolizing",
770
+ "immobilisation": "immobilization",
771
+ "immobilise": "immobilize",
772
+ "immobilised": "immobilized",
773
+ "immobiliser": "immobilizer",
774
+ "immobilisers": "immobilizers",
775
+ "immobilises": "immobilizes",
776
+ "immobilising": "immobilizing",
777
+ "immortalise": "immortalize",
778
+ "immortalised": "immortalized",
779
+ "immortalises": "immortalizes",
780
+ "immortalising": "immortalizing",
781
+ "immunisation": "immunization",
782
+ "immunise": "immunize",
783
+ "immunised": "immunized",
784
+ "immunises": "immunizes",
785
+ "immunising": "immunizing",
786
+ "impanelled": "impaneled",
787
+ "impanelling": "impaneling",
788
+ "imperilled": "imperiled",
789
+ "imperilling": "imperiling",
790
+ "individualise": "individualize",
791
+ "individualised": "individualized",
792
+ "individualises": "individualizes",
793
+ "individualising": "individualizing",
794
+ "industrialise": "industrialize",
795
+ "industrialised": "industrialized",
796
+ "industrialises": "industrializes",
797
+ "industrialising": "industrializing",
798
+ "inflexion": "inflection",
799
+ "inflexions": "inflections",
800
+ "initialise": "initialize",
801
+ "initialised": "initialized",
802
+ "initialises": "initializes",
803
+ "initialising": "initializing",
804
+ "initialled": "initialed",
805
+ "initialling": "initialing",
806
+ "instal": "install",
807
+ "instalment": "installment",
808
+ "instalments": "installments",
809
+ "instals": "installs",
810
+ "instil": "instill",
811
+ "instils": "instills",
812
+ "institutionalisation": "institutionalization",
813
+ "institutionalise": "institutionalize",
814
+ "institutionalised": "institutionalized",
815
+ "institutionalises": "institutionalizes",
816
+ "institutionalising": "institutionalizing",
817
+ "intellectualise": "intellectualize",
818
+ "intellectualised": "intellectualized",
819
+ "intellectualises": "intellectualizes",
820
+ "intellectualising": "intellectualizing",
821
+ "internalisation": "internalization",
822
+ "internalise": "internalize",
823
+ "internalised": "internalized",
824
+ "internalises": "internalizes",
825
+ "internalising": "internalizing",
826
+ "internationalisation": "internationalization",
827
+ "internationalise": "internationalize",
828
+ "internationalised": "internationalized",
829
+ "internationalises": "internationalizes",
830
+ "internationalising": "internationalizing",
831
+ "ionisation": "ionization",
832
+ "ionise": "ionize",
833
+ "ionised": "ionized",
834
+ "ioniser": "ionizer",
835
+ "ionisers": "ionizers",
836
+ "ionises": "ionizes",
837
+ "ionising": "ionizing",
838
+ "italicise": "italicize",
839
+ "italicised": "italicized",
840
+ "italicises": "italicizes",
841
+ "italicising": "italicizing",
842
+ "itemise": "itemize",
843
+ "itemised": "itemized",
844
+ "itemises": "itemizes",
845
+ "itemising": "itemizing",
846
+ "jeopardise": "jeopardize",
847
+ "jeopardised": "jeopardized",
848
+ "jeopardises": "jeopardizes",
849
+ "jeopardising": "jeopardizing",
850
+ "jewelled": "jeweled",
851
+ "jeweller": "jeweler",
852
+ "jewellers": "jewelers",
853
+ "jewellery": "jewelry",
854
+ "judgement": "judgment",
855
+ "kilogramme": "kilogram",
856
+ "kilogrammes": "kilograms",
857
+ "kilometre": "kilometer",
858
+ "kilometres": "kilometers",
859
+ "labelled": "labeled",
860
+ "labelling": "labeling",
861
+ "labour": "labor",
862
+ "laboured": "labored",
863
+ "labourer": "laborer",
864
+ "labourers": "laborers",
865
+ "labouring": "laboring",
866
+ "labours": "labors",
867
+ "lacklustre": "lackluster",
868
+ "legalisation": "legalization",
869
+ "legalise": "legalize",
870
+ "legalised": "legalized",
871
+ "legalises": "legalizes",
872
+ "legalising": "legalizing",
873
+ "legitimise": "legitimize",
874
+ "legitimised": "legitimized",
875
+ "legitimises": "legitimizes",
876
+ "legitimising": "legitimizing",
877
+ "leukaemia": "leukemia",
878
+ "levelled": "leveled",
879
+ "leveller": "leveler",
880
+ "levellers": "levelers",
881
+ "levelling": "leveling",
882
+ "libelled": "libeled",
883
+ "libelling": "libeling",
884
+ "libellous": "libelous",
885
+ "liberalisation": "liberalization",
886
+ "liberalise": "liberalize",
887
+ "liberalised": "liberalized",
888
+ "liberalises": "liberalizes",
889
+ "liberalising": "liberalizing",
890
+ "licence": "license",
891
+ "licenced": "licensed",
892
+ "licences": "licenses",
893
+ "licencing": "licensing",
894
+ "likeable": "likable",
895
+ "lionisation": "lionization",
896
+ "lionise": "lionize",
897
+ "lionised": "lionized",
898
+ "lionises": "lionizes",
899
+ "lionising": "lionizing",
900
+ "liquidise": "liquidize",
901
+ "liquidised": "liquidized",
902
+ "liquidiser": "liquidizer",
903
+ "liquidisers": "liquidizers",
904
+ "liquidises": "liquidizes",
905
+ "liquidising": "liquidizing",
906
+ "litre": "liter",
907
+ "litres": "liters",
908
+ "localise": "localize",
909
+ "localised": "localized",
910
+ "localises": "localizes",
911
+ "localising": "localizing",
912
+ "louvre": "louver",
913
+ "louvred": "louvered",
914
+ "louvres": "louvers",
915
+ "lustre": "luster",
916
+ "magnetise": "magnetize",
917
+ "magnetised": "magnetized",
918
+ "magnetises": "magnetizes",
919
+ "magnetising": "magnetizing",
920
+ "manoeuvrability": "maneuverability",
921
+ "manoeuvrable": "maneuverable",
922
+ "manoeuvre": "maneuver",
923
+ "manoeuvred": "maneuvered",
924
+ "manoeuvres": "maneuvers",
925
+ "manoeuvring": "maneuvering",
926
+ "manoeuvrings": "maneuverings",
927
+ "marginalisation": "marginalization",
928
+ "marginalise": "marginalize",
929
+ "marginalised": "marginalized",
930
+ "marginalises": "marginalizes",
931
+ "marginalising": "marginalizing",
932
+ "marshalled": "marshaled",
933
+ "marshalling": "marshaling",
934
+ "marvelled": "marveled",
935
+ "marvelling": "marveling",
936
+ "marvellous": "marvelous",
937
+ "marvellously": "marvelously",
938
+ "materialisation": "materialization",
939
+ "materialise": "materialize",
940
+ "materialised": "materialized",
941
+ "materialises": "materializes",
942
+ "materialising": "materializing",
943
+ "maximisation": "maximization",
944
+ "maximise": "maximize",
945
+ "maximised": "maximized",
946
+ "maximises": "maximizes",
947
+ "maximising": "maximizing",
948
+ "meagre": "meager",
949
+ "mechanisation": "mechanization",
950
+ "mechanise": "mechanize",
951
+ "mechanised": "mechanized",
952
+ "mechanises": "mechanizes",
953
+ "mechanising": "mechanizing",
954
+ "mediaeval": "medieval",
955
+ "memorialise": "memorialize",
956
+ "memorialised": "memorialized",
957
+ "memorialises": "memorializes",
958
+ "memorialising": "memorializing",
959
+ "memorise": "memorize",
960
+ "memorised": "memorized",
961
+ "memorises": "memorizes",
962
+ "memorising": "memorizing",
963
+ "mesmerise": "mesmerize",
964
+ "mesmerised": "mesmerized",
965
+ "mesmerises": "mesmerizes",
966
+ "mesmerising": "mesmerizing",
967
+ "metabolise": "metabolize",
968
+ "metabolised": "metabolized",
969
+ "metabolises": "metabolizes",
970
+ "metabolising": "metabolizing",
971
+ "metre": "meter",
972
+ "metres": "meters",
973
+ "mhm": "hmm",
974
+ "micrometre": "micrometer",
975
+ "micrometres": "micrometers",
976
+ "militarise": "militarize",
977
+ "militarised": "militarized",
978
+ "militarises": "militarizes",
979
+ "militarising": "militarizing",
980
+ "milligramme": "milligram",
981
+ "milligrammes": "milligrams",
982
+ "millilitre": "milliliter",
983
+ "millilitres": "milliliters",
984
+ "millimetre": "millimeter",
985
+ "millimetres": "millimeters",
986
+ "miniaturisation": "miniaturization",
987
+ "miniaturise": "miniaturize",
988
+ "miniaturised": "miniaturized",
989
+ "miniaturises": "miniaturizes",
990
+ "miniaturising": "miniaturizing",
991
+ "minibusses": "minibuses",
992
+ "minimise": "minimize",
993
+ "minimised": "minimized",
994
+ "minimises": "minimizes",
995
+ "minimising": "minimizing",
996
+ "misbehaviour": "misbehavior",
997
+ "misdemeanour": "misdemeanor",
998
+ "misdemeanours": "misdemeanors",
999
+ "misspelt": "misspelled",
1000
+ "mitre": "miter",
1001
+ "mitres": "miters",
1002
+ "mm": "hmm",
1003
+ "mmm": "hmm",
1004
+ "mobilisation": "mobilization",
1005
+ "mobilise": "mobilize",
1006
+ "mobilised": "mobilized",
1007
+ "mobilises": "mobilizes",
1008
+ "mobilising": "mobilizing",
1009
+ "modelled": "modeled",
1010
+ "modeller": "modeler",
1011
+ "modellers": "modelers",
1012
+ "modelling": "modeling",
1013
+ "modernise": "modernize",
1014
+ "modernised": "modernized",
1015
+ "modernises": "modernizes",
1016
+ "modernising": "modernizing",
1017
+ "moisturise": "moisturize",
1018
+ "moisturised": "moisturized",
1019
+ "moisturiser": "moisturizer",
1020
+ "moisturisers": "moisturizers",
1021
+ "moisturises": "moisturizes",
1022
+ "moisturising": "moisturizing",
1023
+ "monologue": "monolog",
1024
+ "monologues": "monologs",
1025
+ "monopolisation": "monopolization",
1026
+ "monopolise": "monopolize",
1027
+ "monopolised": "monopolized",
1028
+ "monopolises": "monopolizes",
1029
+ "monopolising": "monopolizing",
1030
+ "moralise": "moralize",
1031
+ "moralised": "moralized",
1032
+ "moralises": "moralizes",
1033
+ "moralising": "moralizing",
1034
+ "motorised": "motorized",
1035
+ "mould": "mold",
1036
+ "moulded": "molded",
1037
+ "moulder": "molder",
1038
+ "mouldered": "moldered",
1039
+ "mouldering": "moldering",
1040
+ "moulders": "molders",
1041
+ "mouldier": "moldier",
1042
+ "mouldiest": "moldiest",
1043
+ "moulding": "molding",
1044
+ "mouldings": "moldings",
1045
+ "moulds": "molds",
1046
+ "mouldy": "moldy",
1047
+ "moult": "molt",
1048
+ "moulted": "molted",
1049
+ "moulting": "molting",
1050
+ "moults": "molts",
1051
+ "moustache": "mustache",
1052
+ "moustached": "mustached",
1053
+ "moustaches": "mustaches",
1054
+ "moustachioed": "mustachioed",
1055
+ "multicoloured": "multicolored",
1056
+ "nationalisation": "nationalization",
1057
+ "nationalisations": "nationalizations",
1058
+ "nationalise": "nationalize",
1059
+ "nationalised": "nationalized",
1060
+ "nationalises": "nationalizes",
1061
+ "nationalising": "nationalizing",
1062
+ "naturalisation": "naturalization",
1063
+ "naturalise": "naturalize",
1064
+ "naturalised": "naturalized",
1065
+ "naturalises": "naturalizes",
1066
+ "naturalising": "naturalizing",
1067
+ "neighbour": "neighbor",
1068
+ "neighbourhood": "neighborhood",
1069
+ "neighbourhoods": "neighborhoods",
1070
+ "neighbouring": "neighboring",
1071
+ "neighbourliness": "neighborliness",
1072
+ "neighbourly": "neighborly",
1073
+ "neighbours": "neighbors",
1074
+ "neutralisation": "neutralization",
1075
+ "neutralise": "neutralize",
1076
+ "neutralised": "neutralized",
1077
+ "neutralises": "neutralizes",
1078
+ "neutralising": "neutralizing",
1079
+ "normalisation": "normalization",
1080
+ "normalise": "normalize",
1081
+ "normalised": "normalized",
1082
+ "normalises": "normalizes",
1083
+ "normalising": "normalizing",
1084
+ "odour": "odor",
1085
+ "odourless": "odorless",
1086
+ "odours": "odors",
1087
+ "oesophagus": "esophagus",
1088
+ "oesophaguses": "esophaguses",
1089
+ "oestrogen": "estrogen",
1090
+ "offence": "offense",
1091
+ "offences": "offenses",
1092
+ "omelette": "omelet",
1093
+ "omelettes": "omelets",
1094
+ "optimise": "optimize",
1095
+ "optimised": "optimized",
1096
+ "optimises": "optimizes",
1097
+ "optimising": "optimizing",
1098
+ "organisation": "organization",
1099
+ "organisational": "organizational",
1100
+ "organisations": "organizations",
1101
+ "organise": "organize",
1102
+ "organised": "organized",
1103
+ "organiser": "organizer",
1104
+ "organisers": "organizers",
1105
+ "organises": "organizes",
1106
+ "organising": "organizing",
1107
+ "orthopaedic": "orthopedic",
1108
+ "orthopaedics": "orthopedics",
1109
+ "ostracise": "ostracize",
1110
+ "ostracised": "ostracized",
1111
+ "ostracises": "ostracizes",
1112
+ "ostracising": "ostracizing",
1113
+ "outmanoeuvre": "outmaneuver",
1114
+ "outmanoeuvred": "outmaneuvered",
1115
+ "outmanoeuvres": "outmaneuvers",
1116
+ "outmanoeuvring": "outmaneuvering",
1117
+ "overemphasise": "overemphasize",
1118
+ "overemphasised": "overemphasized",
1119
+ "overemphasises": "overemphasizes",
1120
+ "overemphasising": "overemphasizing",
1121
+ "oxidisation": "oxidization",
1122
+ "oxidise": "oxidize",
1123
+ "oxidised": "oxidized",
1124
+ "oxidises": "oxidizes",
1125
+ "oxidising": "oxidizing",
1126
+ "paederast": "pederast",
1127
+ "paederasts": "pederasts",
1128
+ "paediatric": "pediatric",
1129
+ "paediatrician": "pediatrician",
1130
+ "paediatricians": "pediatricians",
1131
+ "paediatrics": "pediatrics",
1132
+ "paedophile": "pedophile",
1133
+ "paedophiles": "pedophiles",
1134
+ "paedophilia": "pedophilia",
1135
+ "palaeolithic": "paleolithic",
1136
+ "palaeontologist": "paleontologist",
1137
+ "palaeontologists": "paleontologists",
1138
+ "palaeontology": "paleontology",
1139
+ "panelled": "paneled",
1140
+ "panelling": "paneling",
1141
+ "panellist": "panelist",
1142
+ "panellists": "panelists",
1143
+ "paralyse": "paralyze",
1144
+ "paralysed": "paralyzed",
1145
+ "paralyses": "paralyzes",
1146
+ "paralysing": "paralyzing",
1147
+ "parcelled": "parceled",
1148
+ "parcelling": "parceling",
1149
+ "parlour": "parlor",
1150
+ "parlours": "parlors",
1151
+ "particularise": "particularize",
1152
+ "particularised": "particularized",
1153
+ "particularises": "particularizes",
1154
+ "particularising": "particularizing",
1155
+ "passivisation": "passivization",
1156
+ "passivise": "passivize",
1157
+ "passivised": "passivized",
1158
+ "passivises": "passivizes",
1159
+ "passivising": "passivizing",
1160
+ "pasteurisation": "pasteurization",
1161
+ "pasteurise": "pasteurize",
1162
+ "pasteurised": "pasteurized",
1163
+ "pasteurises": "pasteurizes",
1164
+ "pasteurising": "pasteurizing",
1165
+ "patronise": "patronize",
1166
+ "patronised": "patronized",
1167
+ "patronises": "patronizes",
1168
+ "patronising": "patronizing",
1169
+ "patronisingly": "patronizingly",
1170
+ "pedalled": "pedaled",
1171
+ "pedalling": "pedaling",
1172
+ "pedestrianisation": "pedestrianization",
1173
+ "pedestrianise": "pedestrianize",
1174
+ "pedestrianised": "pedestrianized",
1175
+ "pedestrianises": "pedestrianizes",
1176
+ "pedestrianising": "pedestrianizing",
1177
+ "penalise": "penalize",
1178
+ "penalised": "penalized",
1179
+ "penalises": "penalizes",
1180
+ "penalising": "penalizing",
1181
+ "pencilled": "penciled",
1182
+ "pencilling": "penciling",
1183
+ "personalise": "personalize",
1184
+ "personalised": "personalized",
1185
+ "personalises": "personalizes",
1186
+ "personalising": "personalizing",
1187
+ "pharmacopoeia": "pharmacopeia",
1188
+ "pharmacopoeias": "pharmacopeias",
1189
+ "philosophise": "philosophize",
1190
+ "philosophised": "philosophized",
1191
+ "philosophises": "philosophizes",
1192
+ "philosophising": "philosophizing",
1193
+ "philtre": "filter",
1194
+ "philtres": "filters",
1195
+ "phoney": "phony",
1196
+ "plagiarise": "plagiarize",
1197
+ "plagiarised": "plagiarized",
1198
+ "plagiarises": "plagiarizes",
1199
+ "plagiarising": "plagiarizing",
1200
+ "plough": "plow",
1201
+ "ploughed": "plowed",
1202
+ "ploughing": "plowing",
1203
+ "ploughman": "plowman",
1204
+ "ploughmen": "plowmen",
1205
+ "ploughs": "plows",
1206
+ "ploughshare": "plowshare",
1207
+ "ploughshares": "plowshares",
1208
+ "polarisation": "polarization",
1209
+ "polarise": "polarize",
1210
+ "polarised": "polarized",
1211
+ "polarises": "polarizes",
1212
+ "polarising": "polarizing",
1213
+ "politicisation": "politicization",
1214
+ "politicise": "politicize",
1215
+ "politicised": "politicized",
1216
+ "politicises": "politicizes",
1217
+ "politicising": "politicizing",
1218
+ "popularisation": "popularization",
1219
+ "popularise": "popularize",
1220
+ "popularised": "popularized",
1221
+ "popularises": "popularizes",
1222
+ "popularising": "popularizing",
1223
+ "pouffe": "pouf",
1224
+ "pouffes": "poufs",
1225
+ "practise": "practice",
1226
+ "practised": "practiced",
1227
+ "practises": "practices",
1228
+ "practising": "practicing",
1229
+ "praesidium": "presidium",
1230
+ "praesidiums": "presidiums",
1231
+ "pressurisation": "pressurization",
1232
+ "pressurise": "pressurize",
1233
+ "pressurised": "pressurized",
1234
+ "pressurises": "pressurizes",
1235
+ "pressurising": "pressurizing",
1236
+ "pretence": "pretense",
1237
+ "pretences": "pretenses",
1238
+ "primaeval": "primeval",
1239
+ "prioritisation": "prioritization",
1240
+ "prioritise": "prioritize",
1241
+ "prioritised": "prioritized",
1242
+ "prioritises": "prioritizes",
1243
+ "prioritising": "prioritizing",
1244
+ "privatisation": "privatization",
1245
+ "privatisations": "privatizations",
1246
+ "privatise": "privatize",
1247
+ "privatised": "privatized",
1248
+ "privatises": "privatizes",
1249
+ "privatising": "privatizing",
1250
+ "professionalisation": "professionalization",
1251
+ "professionalise": "professionalize",
1252
+ "professionalised": "professionalized",
1253
+ "professionalises": "professionalizes",
1254
+ "professionalising": "professionalizing",
1255
+ "programme": "program",
1256
+ "programmes": "programs",
1257
+ "prologue": "prolog",
1258
+ "prologues": "prologs",
1259
+ "propagandise": "propagandize",
1260
+ "propagandised": "propagandized",
1261
+ "propagandises": "propagandizes",
1262
+ "propagandising": "propagandizing",
1263
+ "proselytise": "proselytize",
1264
+ "proselytised": "proselytized",
1265
+ "proselytiser": "proselytizer",
1266
+ "proselytisers": "proselytizers",
1267
+ "proselytises": "proselytizes",
1268
+ "proselytising": "proselytizing",
1269
+ "psychoanalyse": "psychoanalyze",
1270
+ "psychoanalysed": "psychoanalyzed",
1271
+ "psychoanalyses": "psychoanalyzes",
1272
+ "psychoanalysing": "psychoanalyzing",
1273
+ "publicise": "publicize",
1274
+ "publicised": "publicized",
1275
+ "publicises": "publicizes",
1276
+ "publicising": "publicizing",
1277
+ "pulverisation": "pulverization",
1278
+ "pulverise": "pulverize",
1279
+ "pulverised": "pulverized",
1280
+ "pulverises": "pulverizes",
1281
+ "pulverising": "pulverizing",
1282
+ "pummelled": "pummel",
1283
+ "pummelling": "pummeled",
1284
+ "pyjama": "pajama",
1285
+ "pyjamas": "pajamas",
1286
+ "pzazz": "pizzazz",
1287
+ "quarrelled": "quarreled",
1288
+ "quarrelling": "quarreling",
1289
+ "radicalise": "radicalize",
1290
+ "radicalised": "radicalized",
1291
+ "radicalises": "radicalizes",
1292
+ "radicalising": "radicalizing",
1293
+ "rancour": "rancor",
1294
+ "randomise": "randomize",
1295
+ "randomised": "randomized",
1296
+ "randomises": "randomizes",
1297
+ "randomising": "randomizing",
1298
+ "rationalisation": "rationalization",
1299
+ "rationalisations": "rationalizations",
1300
+ "rationalise": "rationalize",
1301
+ "rationalised": "rationalized",
1302
+ "rationalises": "rationalizes",
1303
+ "rationalising": "rationalizing",
1304
+ "ravelled": "raveled",
1305
+ "ravelling": "raveling",
1306
+ "realisable": "realizable",
1307
+ "realisation": "realization",
1308
+ "realisations": "realizations",
1309
+ "realise": "realize",
1310
+ "realised": "realized",
1311
+ "realises": "realizes",
1312
+ "realising": "realizing",
1313
+ "recognisable": "recognizable",
1314
+ "recognisably": "recognizably",
1315
+ "recognisance": "recognizance",
1316
+ "recognise": "recognize",
1317
+ "recognised": "recognized",
1318
+ "recognises": "recognizes",
1319
+ "recognising": "recognizing",
1320
+ "reconnoitre": "reconnoiter",
1321
+ "reconnoitred": "reconnoitered",
1322
+ "reconnoitres": "reconnoiters",
1323
+ "reconnoitring": "reconnoitering",
1324
+ "refuelled": "refueled",
1325
+ "refuelling": "refueling",
1326
+ "regularisation": "regularization",
1327
+ "regularise": "regularize",
1328
+ "regularised": "regularized",
1329
+ "regularises": "regularizes",
1330
+ "regularising": "regularizing",
1331
+ "remodelled": "remodeled",
1332
+ "remodelling": "remodeling",
1333
+ "remould": "remold",
1334
+ "remoulded": "remolded",
1335
+ "remoulding": "remolding",
1336
+ "remoulds": "remolds",
1337
+ "reorganisation": "reorganization",
1338
+ "reorganisations": "reorganizations",
1339
+ "reorganise": "reorganize",
1340
+ "reorganised": "reorganized",
1341
+ "reorganises": "reorganizes",
1342
+ "reorganising": "reorganizing",
1343
+ "revelled": "reveled",
1344
+ "reveller": "reveler",
1345
+ "revellers": "revelers",
1346
+ "revelling": "reveling",
1347
+ "revitalise": "revitalize",
1348
+ "revitalised": "revitalized",
1349
+ "revitalises": "revitalizes",
1350
+ "revitalising": "revitalizing",
1351
+ "revolutionise": "revolutionize",
1352
+ "revolutionised": "revolutionized",
1353
+ "revolutionises": "revolutionizes",
1354
+ "revolutionising": "revolutionizing",
1355
+ "rhapsodise": "rhapsodize",
1356
+ "rhapsodised": "rhapsodized",
1357
+ "rhapsodises": "rhapsodizes",
1358
+ "rhapsodising": "rhapsodizing",
1359
+ "rigour": "rigor",
1360
+ "rigours": "rigors",
1361
+ "ritualised": "ritualized",
1362
+ "rivalled": "rivaled",
1363
+ "rivalling": "rivaling",
1364
+ "romanticise": "romanticize",
1365
+ "romanticised": "romanticized",
1366
+ "romanticises": "romanticizes",
1367
+ "romanticising": "romanticizing",
1368
+ "rumour": "rumor",
1369
+ "rumoured": "rumored",
1370
+ "rumours": "rumors",
1371
+ "sabre": "saber",
1372
+ "sabres": "sabers",
1373
+ "saltpetre": "saltpeter",
1374
+ "sanitise": "sanitize",
1375
+ "sanitised": "sanitized",
1376
+ "sanitises": "sanitizes",
1377
+ "sanitising": "sanitizing",
1378
+ "satirise": "satirize",
1379
+ "satirised": "satirized",
1380
+ "satirises": "satirizes",
1381
+ "satirising": "satirizing",
1382
+ "saviour": "savior",
1383
+ "saviours": "saviors",
1384
+ "savour": "savor",
1385
+ "savoured": "savored",
1386
+ "savouries": "savories",
1387
+ "savouring": "savoring",
1388
+ "savours": "savors",
1389
+ "savoury": "savory",
1390
+ "scandalise": "scandalize",
1391
+ "scandalised": "scandalized",
1392
+ "scandalises": "scandalizes",
1393
+ "scandalising": "scandalizing",
1394
+ "sceptic": "skeptic",
1395
+ "sceptical": "skeptical",
1396
+ "sceptically": "skeptically",
1397
+ "scepticism": "skepticism",
1398
+ "sceptics": "skeptics",
1399
+ "sceptre": "scepter",
1400
+ "sceptres": "scepters",
1401
+ "scrutinise": "scrutinize",
1402
+ "scrutinised": "scrutinized",
1403
+ "scrutinises": "scrutinizes",
1404
+ "scrutinising": "scrutinizing",
1405
+ "secularisation": "secularization",
1406
+ "secularise": "secularize",
1407
+ "secularised": "secularized",
1408
+ "secularises": "secularizes",
1409
+ "secularising": "secularizing",
1410
+ "sensationalise": "sensationalize",
1411
+ "sensationalised": "sensationalized",
1412
+ "sensationalises": "sensationalizes",
1413
+ "sensationalising": "sensationalizing",
1414
+ "sensitise": "sensitize",
1415
+ "sensitised": "sensitized",
1416
+ "sensitises": "sensitizes",
1417
+ "sensitising": "sensitizing",
1418
+ "sentimentalise": "sentimentalize",
1419
+ "sentimentalised": "sentimentalized",
1420
+ "sentimentalises": "sentimentalizes",
1421
+ "sentimentalising": "sentimentalizing",
1422
+ "sepulchre": "sepulcher",
1423
+ "sepulchres": "sepulchers",
1424
+ "serialisation": "serialization",
1425
+ "serialisations": "serializations",
1426
+ "serialise": "serialize",
1427
+ "serialised": "serialized",
1428
+ "serialises": "serializes",
1429
+ "serialising": "serializing",
1430
+ "sermonise": "sermonize",
1431
+ "sermonised": "sermonized",
1432
+ "sermonises": "sermonizes",
1433
+ "sermonising": "sermonizing",
1434
+ "sheikh": "sheik",
1435
+ "shovelled": "shoveled",
1436
+ "shovelling": "shoveling",
1437
+ "shrivelled": "shriveled",
1438
+ "shrivelling": "shriveling",
1439
+ "signalise": "signalize",
1440
+ "signalised": "signalized",
1441
+ "signalises": "signalizes",
1442
+ "signalising": "signalizing",
1443
+ "signalled": "signaled",
1444
+ "signalling": "signaling",
1445
+ "smoulder": "smolder",
1446
+ "smouldered": "smoldered",
1447
+ "smouldering": "smoldering",
1448
+ "smoulders": "smolders",
1449
+ "snivelled": "sniveled",
1450
+ "snivelling": "sniveling",
1451
+ "snorkelled": "snorkeled",
1452
+ "snorkelling": "snorkeling",
1453
+ "snowplough": "snowplow",
1454
+ "snowploughs": "snowplow",
1455
+ "socialisation": "socialization",
1456
+ "socialise": "socialize",
1457
+ "socialised": "socialized",
1458
+ "socialises": "socializes",
1459
+ "socialising": "socializing",
1460
+ "sodomise": "sodomize",
1461
+ "sodomised": "sodomized",
1462
+ "sodomises": "sodomizes",
1463
+ "sodomising": "sodomizing",
1464
+ "solemnise": "solemnize",
1465
+ "solemnised": "solemnized",
1466
+ "solemnises": "solemnizes",
1467
+ "solemnising": "solemnizing",
1468
+ "sombre": "somber",
1469
+ "specialisation": "specialization",
1470
+ "specialisations": "specializations",
1471
+ "specialise": "specialize",
1472
+ "specialised": "specialized",
1473
+ "specialises": "specializes",
1474
+ "specialising": "specializing",
1475
+ "spectre": "specter",
1476
+ "spectres": "specters",
1477
+ "spiralled": "spiraled",
1478
+ "spiralling": "spiraling",
1479
+ "splendour": "splendor",
1480
+ "splendours": "splendors",
1481
+ "squirrelled": "squirreled",
1482
+ "squirrelling": "squirreling",
1483
+ "stabilisation": "stabilization",
1484
+ "stabilise": "stabilize",
1485
+ "stabilised": "stabilized",
1486
+ "stabiliser": "stabilizer",
1487
+ "stabilisers": "stabilizers",
1488
+ "stabilises": "stabilizes",
1489
+ "stabilising": "stabilizing",
1490
+ "standardisation": "standardization",
1491
+ "standardise": "standardize",
1492
+ "standardised": "standardized",
1493
+ "standardises": "standardizes",
1494
+ "standardising": "standardizing",
1495
+ "stencilled": "stenciled",
1496
+ "stencilling": "stenciling",
1497
+ "sterilisation": "sterilization",
1498
+ "sterilisations": "sterilizations",
1499
+ "sterilise": "sterilize",
1500
+ "sterilised": "sterilized",
1501
+ "steriliser": "sterilizer",
1502
+ "sterilisers": "sterilizers",
1503
+ "sterilises": "sterilizes",
1504
+ "sterilising": "sterilizing",
1505
+ "stigmatisation": "stigmatization",
1506
+ "stigmatise": "stigmatize",
1507
+ "stigmatised": "stigmatized",
1508
+ "stigmatises": "stigmatizes",
1509
+ "stigmatising": "stigmatizing",
1510
+ "storey": "story",
1511
+ "storeys": "stories",
1512
+ "subsidisation": "subsidization",
1513
+ "subsidise": "subsidize",
1514
+ "subsidised": "subsidized",
1515
+ "subsidiser": "subsidizer",
1516
+ "subsidisers": "subsidizers",
1517
+ "subsidises": "subsidizes",
1518
+ "subsidising": "subsidizing",
1519
+ "succour": "succor",
1520
+ "succoured": "succored",
1521
+ "succouring": "succoring",
1522
+ "succours": "succors",
1523
+ "sulphate": "sulfate",
1524
+ "sulphates": "sulfates",
1525
+ "sulphide": "sulfide",
1526
+ "sulphides": "sulfides",
1527
+ "sulphur": "sulfur",
1528
+ "sulphurous": "sulfurous",
1529
+ "summarise": "summarize",
1530
+ "summarised": "summarized",
1531
+ "summarises": "summarizes",
1532
+ "summarising": "summarizing",
1533
+ "swivelled": "swiveled",
1534
+ "swivelling": "swiveling",
1535
+ "symbolise": "symbolize",
1536
+ "symbolised": "symbolized",
1537
+ "symbolises": "symbolizes",
1538
+ "symbolising": "symbolizing",
1539
+ "sympathise": "sympathize",
1540
+ "sympathised": "sympathized",
1541
+ "sympathiser": "sympathizer",
1542
+ "sympathisers": "sympathizers",
1543
+ "sympathises": "sympathizes",
1544
+ "sympathising": "sympathizing",
1545
+ "synchronisation": "synchronization",
1546
+ "synchronise": "synchronize",
1547
+ "synchronised": "synchronized",
1548
+ "synchronises": "synchronizes",
1549
+ "synchronising": "synchronizing",
1550
+ "synthesise": "synthesize",
1551
+ "synthesised": "synthesized",
1552
+ "synthesiser": "synthesizer",
1553
+ "synthesisers": "synthesizers",
1554
+ "synthesises": "synthesizes",
1555
+ "synthesising": "synthesizing",
1556
+ "syphon": "siphon",
1557
+ "syphoned": "siphoned",
1558
+ "syphoning": "siphoning",
1559
+ "syphons": "siphons",
1560
+ "systematisation": "systematization",
1561
+ "systematise": "systematize",
1562
+ "systematised": "systematized",
1563
+ "systematises": "systematizes",
1564
+ "systematising": "systematizing",
1565
+ "tantalise": "tantalize",
1566
+ "tantalised": "tantalized",
1567
+ "tantalises": "tantalizes",
1568
+ "tantalising": "tantalizing",
1569
+ "tantalisingly": "tantalizingly",
1570
+ "tasselled": "tasseled",
1571
+ "technicolour": "technicolor",
1572
+ "temporise": "temporize",
1573
+ "temporised": "temporized",
1574
+ "temporises": "temporizes",
1575
+ "temporising": "temporizing",
1576
+ "tenderise": "tenderize",
1577
+ "tenderised": "tenderized",
1578
+ "tenderises": "tenderizes",
1579
+ "tenderising": "tenderizing",
1580
+ "terrorise": "terrorize",
1581
+ "terrorised": "terrorized",
1582
+ "terrorises": "terrorizes",
1583
+ "terrorising": "terrorizing",
1584
+ "theatre": "theater",
1585
+ "theatregoer": "theatergoer",
1586
+ "theatregoers": "theatergoers",
1587
+ "theatres": "theaters",
1588
+ "theorise": "theorize",
1589
+ "theorised": "theorized",
1590
+ "theorises": "theorizes",
1591
+ "theorising": "theorizing",
1592
+ "tonne": "ton",
1593
+ "tonnes": "tons",
1594
+ "towelled": "toweled",
1595
+ "towelling": "toweling",
1596
+ "toxaemia": "toxemia",
1597
+ "tranquillise": "tranquilize",
1598
+ "tranquillised": "tranquilized",
1599
+ "tranquilliser": "tranquilizer",
1600
+ "tranquillisers": "tranquilizers",
1601
+ "tranquillises": "tranquilizes",
1602
+ "tranquillising": "tranquilizing",
1603
+ "tranquillity": "tranquility",
1604
+ "tranquillize": "tranquilize",
1605
+ "tranquillized": "tranquilized",
1606
+ "tranquillizer": "tranquilizer",
1607
+ "tranquillizers": "tranquilizers",
1608
+ "tranquillizes": "tranquilizes",
1609
+ "tranquillizing": "tranquilizing",
1610
+ "tranquilly": "tranquility",
1611
+ "transistorised": "transistorized",
1612
+ "traumatise": "traumatize",
1613
+ "traumatised": "traumatized",
1614
+ "traumatises": "traumatizes",
1615
+ "traumatising": "traumatizing",
1616
+ "travelled": "traveled",
1617
+ "traveller": "traveler",
1618
+ "travellers": "travelers",
1619
+ "travelling": "traveling",
1620
+ "travelog": "travelogue",
1621
+ "travelogs": "travelogues",
1622
+ "trialled": "trialed",
1623
+ "trialling": "trialing",
1624
+ "tricolour": "tricolor",
1625
+ "tricolours": "tricolors",
1626
+ "trivialise": "trivialize",
1627
+ "trivialised": "trivialized",
1628
+ "trivialises": "trivializes",
1629
+ "trivialising": "trivializing",
1630
+ "tumour": "tumor",
1631
+ "tumours": "tumors",
1632
+ "tunnelled": "tunneled",
1633
+ "tunnelling": "tunneling",
1634
+ "tyrannise": "tyrannize",
1635
+ "tyrannised": "tyrannized",
1636
+ "tyrannises": "tyrannizes",
1637
+ "tyrannising": "tyrannizing",
1638
+ "tyre": "tire",
1639
+ "tyres": "tires",
1640
+ "unauthorised": "unauthorized",
1641
+ "uncivilised": "uncivilized",
1642
+ "underutilised": "underutilized",
1643
+ "unequalled": "unequaled",
1644
+ "unfavourable": "unfavorable",
1645
+ "unfavourably": "unfavorably",
1646
+ "unionisation": "unionization",
1647
+ "unionise": "unionize",
1648
+ "unionised": "unionized",
1649
+ "unionises": "unionizes",
1650
+ "unionising": "unionizing",
1651
+ "unorganised": "unorganized",
1652
+ "unravelled": "unraveled",
1653
+ "unravelling": "unraveling",
1654
+ "unrecognisable": "unrecognizable",
1655
+ "unrecognised": "unrecognized",
1656
+ "unrivalled": "unrivaled",
1657
+ "unsavoury": "unsavory",
1658
+ "untrammelled": "untrammeled",
1659
+ "urbanisation": "urbanization",
1660
+ "urbanise": "urbanize",
1661
+ "urbanised": "urbanized",
1662
+ "urbanises": "urbanizes",
1663
+ "urbanising": "urbanizing",
1664
+ "utilisable": "utilizable",
1665
+ "utilisation": "utilization",
1666
+ "utilise": "utilize",
1667
+ "utilised": "utilized",
1668
+ "utilises": "utilizes",
1669
+ "utilising": "utilizing",
1670
+ "valour": "valor",
1671
+ "vandalise": "vandalize",
1672
+ "vandalised": "vandalized",
1673
+ "vandalises": "vandalizes",
1674
+ "vandalising": "vandalizing",
1675
+ "vaporisation": "vaporization",
1676
+ "vaporise": "vaporize",
1677
+ "vaporised": "vaporized",
1678
+ "vaporises": "vaporizes",
1679
+ "vaporising": "vaporizing",
1680
+ "vapour": "vapor",
1681
+ "vapours": "vapors",
1682
+ "verbalise": "verbalize",
1683
+ "verbalised": "verbalized",
1684
+ "verbalises": "verbalizes",
1685
+ "verbalising": "verbalizing",
1686
+ "victimisation": "victimization",
1687
+ "victimise": "victimize",
1688
+ "victimised": "victimized",
1689
+ "victimises": "victimizes",
1690
+ "victimising": "victimizing",
1691
+ "videodisc": "videodisk",
1692
+ "videodiscs": "videodisks",
1693
+ "vigour": "vigor",
1694
+ "visualisation": "visualization",
1695
+ "visualisations": "visualizations",
1696
+ "visualise": "visualize",
1697
+ "visualised": "visualized",
1698
+ "visualises": "visualizes",
1699
+ "visualising": "visualizing",
1700
+ "vocalisation": "vocalization",
1701
+ "vocalisations": "vocalizations",
1702
+ "vocalise": "vocalize",
1703
+ "vocalised": "vocalized",
1704
+ "vocalises": "vocalizes",
1705
+ "vocalising": "vocalizing",
1706
+ "vulcanised": "vulcanized",
1707
+ "vulgarisation": "vulgarization",
1708
+ "vulgarise": "vulgarize",
1709
+ "vulgarised": "vulgarized",
1710
+ "vulgarises": "vulgarizes",
1711
+ "vulgarising": "vulgarizing",
1712
+ "waggon": "wagon",
1713
+ "waggons": "wagons",
1714
+ "watercolour": "watercolor",
1715
+ "watercolours": "watercolors",
1716
+ "weaselled": "weaseled",
1717
+ "weaselling": "weaseling",
1718
+ "westernisation": "westernization",
1719
+ "westernise": "westernize",
1720
+ "westernised": "westernized",
1721
+ "westernises": "westernizes",
1722
+ "westernising": "westernizing",
1723
+ "womanise": "womanize",
1724
+ "womanised": "womanized",
1725
+ "womaniser": "womanizer",
1726
+ "womanisers": "womanizers",
1727
+ "womanises": "womanizes",
1728
+ "womanising": "womanizing",
1729
+ "woollen": "woolen",
1730
+ "woollens": "woolens",
1731
+ "woollies": "woolies",
1732
+ "woolly": "wooly",
1733
+ "worshipped": "worshiped",
1734
+ "worshipper": "worshiper",
1735
+ "worshipping": "worshiping",
1736
+ "yodelled": "yodeled",
1737
+ "yodelling": "yodeling",
1738
+ "yoghourt": "yogurt",
1739
+ "yoghourts": "yogurts",
1740
+ "yoghurt": "yogurt",
1741
+ "yoghurts": "yogurts"
1742
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7438f51a1a24da2a3938c9dcc791905bf01cd0715274a901f107109b970393e2
3
+ size 574811514
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d20bd6ca9182d59f627663e1486deccec927b5fa8e7d72ad568fe54cec45d8
3
+ size 14244
run.sh ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python3 run_speech_recognition_seq2seq_streaming.py \
2
+ --model_name_or_path="openai/whisper-base" \
3
+ --dataset_name="google/fleurs" \
4
+ --dataset_config_name="bn_in" \
5
+ --language="bengali" \
6
+ --train_split_name="train+validation" \
7
+ --eval_split_name="test" \
8
+ --model_index_name="Whisper Base Bengali" \
9
+ --max_steps="5000" \
10
+ --output_dir="./" \
11
+ --per_device_train_batch_size="64" \
12
+ --per_device_eval_batch_size="32" \
13
+ --logging_steps="25" \
14
+ --learning_rate="1e-5" \
15
+ --warmup_steps="500" \
16
+ --evaluation_strategy="steps" \
17
+ --eval_steps="1000" \
18
+ --save_strategy="steps" \
19
+ --save_steps="1000" \
20
+ --generation_max_length="225" \
21
+ --length_column_name="input_length" \
22
+ --max_duration_in_seconds="30" \
23
+ --text_column_name="sentence" \
24
+ --freeze_feature_encoder="False" \
25
+ --report_to="tensorboard" \
26
+ --metric_for_best_model="wer" \
27
+ --greater_is_better="False" \
28
+ --load_best_model_at_end \
29
+ --gradient_checkpointing \
30
+ --fp16 \
31
+ --overwrite_output_dir \
32
+ --do_train \
33
+ --do_eval \
34
+ --predict_with_generate \
35
+ --do_normalize_eval \
36
+ --streaming \
37
+ --use_auth_token \
38
+ --push_to_hub
run_cmn.sh ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python3 run_speech_recognition_seq2seq_streaming.py \
2
+ --model_name_or_path="arun100/whisper-base-bn" \
3
+ --dataset_name="mozilla-foundation/common_voice_16_0" \
4
+ --dataset_config_name="bn" \
5
+ --language="bengali" \
6
+ --train_split_name="train+validation" \
7
+ --eval_split_name="test" \
8
+ --model_index_name="Whisper Base Bengali" \
9
+ --max_steps="1000" \
10
+ --output_dir="./" \
11
+ --per_device_train_batch_size="32" \
12
+ --per_device_eval_batch_size="32" \
13
+ --gradient_accumulation_steps=2 \
14
+ --logging_steps="25" \
15
+ --learning_rate="1e-6" \
16
+ --warmup_steps="50" \
17
+ --evaluation_strategy="steps" \
18
+ --eval_steps="500" \
19
+ --save_strategy="steps" \
20
+ --save_steps="500" \
21
+ --generation_max_length="225" \
22
+ --length_column_name="input_length" \
23
+ --max_duration_in_seconds="30" \
24
+ --text_column_name="sentence" \
25
+ --freeze_feature_encoder="False" \
26
+ --report_to="tensorboard" \
27
+ --metric_for_best_model="wer" \
28
+ --greater_is_better="False" \
29
+ --load_best_model_at_end \
30
+ --gradient_checkpointing \
31
+ --fp16 \
32
+ --overwrite_output_dir \
33
+ --do_train \
34
+ --do_eval \
35
+ --predict_with_generate \
36
+ --do_normalize_eval \
37
+ --streaming="False" \
38
+ --use_auth_token \
39
+ --push_to_hub
run_fleurs.sh ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python3 run_speech_recognition_seq2seq_streaming.py \
2
+ --model_name_or_path="arun100/whisper-base-tr-1" \
3
+ --dataset_name="google/fleurs" \
4
+ --dataset_config_name="tr_tr" \
5
+ --language="turkish" \
6
+ --train_split_name="train+validation" \
7
+ --eval_split_name="test" \
8
+ --model_index_name="Whisper Base Turkish" \
9
+ --max_steps="5000" \
10
+ --output_dir="./" \
11
+ --per_device_train_batch_size="32" \
12
+ --per_device_eval_batch_size="32" \
13
+ --gradient_accumulation_steps=2 \
14
+ --logging_steps="25" \
15
+ --learning_rate="1e-6" \
16
+ --warmup_steps="500" \
17
+ --evaluation_strategy="steps" \
18
+ --eval_steps="500" \
19
+ --save_strategy="steps" \
20
+ --save_steps="500" \
21
+ --generation_max_length="225" \
22
+ --length_column_name="input_length" \
23
+ --max_duration_in_seconds="30" \
24
+ --text_column_name="transcription" \
25
+ --freeze_feature_encoder="False" \
26
+ --report_to="tensorboard" \
27
+ --metric_for_best_model="wer" \
28
+ --greater_is_better="False" \
29
+ --load_best_model_at_end \
30
+ --gradient_checkpointing \
31
+ --fp16 \
32
+ --overwrite_output_dir \
33
+ --do_train \
34
+ --do_eval \
35
+ --predict_with_generate \
36
+ --do_normalize_eval \
37
+ --streaming \
38
+ --use_auth_token \
39
+ --push_to_hub
run_speech_recognition_seq2seq_streaming.py ADDED
@@ -0,0 +1,636 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+ # coding=utf-8
3
+ # Copyright 2022 The HuggingFace Team. All rights reserved.
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+ """
17
+ Fine-tuning the library models for sequence to sequence speech recognition
18
+ with 🤗 Datasets' streaming mode.
19
+ """
20
+ # You can also adapt this script for your own sequence to sequence speech
21
+ # recognition task. Pointers for this are left as comments.
22
+
23
+ import logging
24
+ import os
25
+ import sys
26
+ from dataclasses import dataclass, field
27
+ from typing import Any, Dict, List, Optional, Union
28
+
29
+ import datasets
30
+ import torch
31
+ from datasets import DatasetDict, IterableDatasetDict, interleave_datasets, load_dataset
32
+ from torch.utils.data import IterableDataset
33
+
34
+ import evaluate
35
+ import transformers
36
+ from transformers import (
37
+ AutoConfig,
38
+ AutoFeatureExtractor,
39
+ AutoModelForSpeechSeq2Seq,
40
+ AutoProcessor,
41
+ AutoTokenizer,
42
+ HfArgumentParser,
43
+ Seq2SeqTrainer,
44
+ Seq2SeqTrainingArguments,
45
+ TrainerCallback,
46
+ set_seed,
47
+ )
48
+ from transformers.models.whisper.english_normalizer import BasicTextNormalizer
49
+ from transformers.trainer_pt_utils import IterableDatasetShard
50
+ from transformers.trainer_utils import get_last_checkpoint, is_main_process
51
+ from transformers.utils import check_min_version, send_example_telemetry
52
+ from transformers.utils.versions import require_version
53
+
54
+
55
+ # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
56
+ check_min_version("4.25.0.dev0")
57
+
58
+ require_version("datasets>=1.18.2", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
59
+
60
+ logger = logging.getLogger(__name__)
61
+
62
+
63
+ @dataclass
64
+ class ModelArguments:
65
+ """
66
+ Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
67
+ """
68
+
69
+ model_name_or_path: str = field(
70
+ metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
71
+ )
72
+ config_name: Optional[str] = field(
73
+ default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
74
+ )
75
+ tokenizer_name: Optional[str] = field(
76
+ default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
77
+ )
78
+ feature_extractor_name: Optional[str] = field(
79
+ default=None, metadata={"help": "feature extractor name or path if not the same as model_name"}
80
+ )
81
+ cache_dir: Optional[str] = field(
82
+ default=None,
83
+ metadata={"help": "Where to store the pretrained models downloaded from huggingface.co"},
84
+ )
85
+ use_fast_tokenizer: bool = field(
86
+ default=True,
87
+ metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
88
+ )
89
+ model_revision: str = field(
90
+ default="main",
91
+ metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
92
+ )
93
+ use_auth_token: bool = field(
94
+ default=False,
95
+ metadata={
96
+ "help": (
97
+ "Will use the token generated when running `huggingface-cli login` (necessary to use this script "
98
+ "with private models)."
99
+ )
100
+ },
101
+ )
102
+ freeze_feature_encoder: bool = field(
103
+ default=True, metadata={"help": "Whether to freeze the feature encoder layers of the model."}
104
+ )
105
+ freeze_encoder: bool = field(
106
+ default=False, metadata={"help": "Whether to freeze the entire encoder of the seq2seq model."}
107
+ )
108
+ forced_decoder_ids: List[List[int]] = field(
109
+ default=None,
110
+ metadata={
111
+ "help": (
112
+ "A list of pairs of integers which indicates a mapping from generation indices to token indices "
113
+ "that will be forced before sampling. For example, [[0, 123]] means the first generated token "
114
+ "will always be a token of index 123."
115
+ )
116
+ },
117
+ )
118
+ suppress_tokens: List[int] = field(
119
+ default=None, metadata={"help": "A list of tokens that will be suppressed at generation."}
120
+ )
121
+ model_index_name: str = field(default=None, metadata={"help": "Pretty name for the model card."})
122
+
123
+
124
+ @dataclass
125
+ class DataTrainingArguments:
126
+ """
127
+ Arguments pertaining to what data we are going to input our model for training and eval.
128
+ """
129
+
130
+ dataset_name: str = field(
131
+ default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
132
+ )
133
+ dataset_config_name: Optional[str] = field(
134
+ default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
135
+ )
136
+ text_column: Optional[str] = field(
137
+ default=None,
138
+ metadata={"help": "The name of the column in the datasets containing the full texts (for summarization)."},
139
+ )
140
+ max_train_samples: Optional[int] = field(
141
+ default=None,
142
+ metadata={
143
+ "help": (
144
+ "For debugging purposes or quicker training, truncate the number of training examples to this "
145
+ "value if set."
146
+ )
147
+ },
148
+ )
149
+ max_eval_samples: Optional[int] = field(
150
+ default=None,
151
+ metadata={
152
+ "help": (
153
+ "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
154
+ "value if set."
155
+ )
156
+ },
157
+ )
158
+ audio_column_name: str = field(
159
+ default="audio",
160
+ metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
161
+ )
162
+ text_column_name: str = field(
163
+ default="text",
164
+ metadata={"help": "The name of the dataset column containing the text data. Defaults to 'text'"},
165
+ )
166
+ max_duration_in_seconds: float = field(
167
+ default=20.0,
168
+ metadata={
169
+ "help": (
170
+ "Truncate audio files that are longer than `max_duration_in_seconds` seconds to"
171
+ " 'max_duration_in_seconds`"
172
+ )
173
+ },
174
+ )
175
+ min_duration_in_seconds: float = field(
176
+ default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
177
+ )
178
+ train_split_name: str = field(
179
+ default="train",
180
+ metadata={
181
+ "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
182
+ },
183
+ )
184
+ eval_split_name: str = field(
185
+ default="test",
186
+ metadata={
187
+ "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
188
+ },
189
+ )
190
+ do_lower_case: bool = field(
191
+ default=False,
192
+ metadata={"help": "Whether the target text should be lower cased."},
193
+ )
194
+ do_remove_punctuation: bool = field(
195
+ default=False,
196
+ metadata={"help": "Whether the target text should be striped of punctuation."},
197
+ )
198
+ do_normalize_eval: bool = field(
199
+ default=True,
200
+ metadata={"help": "Whether to normalise the references and predictions in the eval WER calculation."},
201
+ )
202
+ language: str = field(
203
+ default=None,
204
+ metadata={
205
+ "help": (
206
+ "Language for multilingual fine-tuning. This argument should be set for multilingual fine-tuning "
207
+ "only. For English speech recognition, it should be set to `None`."
208
+ )
209
+ },
210
+ )
211
+ task: str = field(
212
+ default="transcribe",
213
+ metadata={"help": "Task, either `transcribe` for speech recognition or `translate` for speech translation."},
214
+ )
215
+ shuffle_buffer_size: Optional[int] = field(
216
+ default=500,
217
+ metadata={
218
+ "help": (
219
+ "The number of streamed examples to download before shuffling them. The large the buffer, "
220
+ "the closer it is to real offline shuffling."
221
+ )
222
+ },
223
+ )
224
+ streaming: bool = field(
225
+ default=True,
226
+ metadata={"help": "Whether to use streaming mode to load and pre-process the data."},
227
+ )
228
+
229
+
230
+ @dataclass
231
+ class DataCollatorSpeechSeq2SeqWithPadding:
232
+ """
233
+ Data collator that will dynamically pad the inputs received.
234
+ Args:
235
+ processor ([`WhisperProcessor`])
236
+ The processor used for processing the data.
237
+ decoder_start_token_id (`int`)
238
+ The begin-of-sentence of the decoder.
239
+ """
240
+
241
+ processor: Any
242
+ decoder_start_token_id: int
243
+
244
+ def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
245
+ # split inputs and labels since they have to be of different lengths and need
246
+ # different padding methods
247
+ model_input_name = self.processor.model_input_names[0]
248
+ input_features = [{model_input_name: feature[model_input_name]} for feature in features]
249
+ label_features = [{"input_ids": feature["labels"]} for feature in features]
250
+
251
+ batch = self.processor.feature_extractor.pad(input_features, return_tensors="pt")
252
+
253
+ labels_batch = self.processor.tokenizer.pad(label_features, return_tensors="pt")
254
+
255
+ # replace padding with -100 to ignore loss correctly
256
+ labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)
257
+
258
+ # if bos token is appended in previous tokenization step,
259
+ # cut bos token here as it's append later anyways
260
+ if (labels[:, 0] == self.decoder_start_token_id).all().cpu().item():
261
+ labels = labels[:, 1:]
262
+
263
+ batch["labels"] = labels
264
+
265
+ return batch
266
+
267
+
268
+ def load_maybe_streaming_dataset(dataset_name, dataset_config_name, split="train", streaming=True, **kwargs):
269
+ """
270
+ Utility function to load a dataset in streaming mode. For datasets with multiple splits,
271
+ each split is loaded individually and then splits combined by taking alternating examples from
272
+ each (interleaving).
273
+ """
274
+ if "+" in split:
275
+ # load multiple splits separated by the `+` symbol with streaming mode
276
+ dataset_splits = [
277
+ load_dataset(dataset_name, dataset_config_name, split=split_name, streaming=streaming, **kwargs)
278
+ for split_name in split.split("+")
279
+ ]
280
+ # interleave multiple splits to form one dataset
281
+ interleaved_dataset = interleave_datasets(dataset_splits)
282
+ return interleaved_dataset
283
+ else:
284
+ # load a single split *with* streaming mode
285
+ dataset = load_dataset(dataset_name, dataset_config_name, split=split, streaming=streaming, **kwargs)
286
+ return dataset
287
+
288
+
289
+ def main():
290
+ # 1. Parse input arguments
291
+ # See all possible arguments in src/transformers/training_args.py
292
+ # or by passing the --help flag to this script.
293
+ # We now keep distinct sets of args, for a cleaner separation of concerns.
294
+ parser = HfArgumentParser((ModelArguments, DataTrainingArguments, Seq2SeqTrainingArguments))
295
+
296
+ if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
297
+ # If we pass only one argument to the script and it's the path to a json file,
298
+ # let's parse it to get our arguments.
299
+ model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
300
+ else:
301
+ model_args, data_args, training_args = parser.parse_args_into_dataclasses()
302
+
303
+ # Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
304
+ # information sent is the one passed as arguments along with your Python/PyTorch versions.
305
+ send_example_telemetry("run_speech_recognition_seq2seq_streaming", model_args, data_args)
306
+
307
+ # 2. Setup logging
308
+ logging.basicConfig(
309
+ format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
310
+ datefmt="%m/%d/%Y %H:%M:%S",
311
+ handlers=[logging.StreamHandler(sys.stdout)],
312
+ )
313
+ log_level = training_args.get_process_log_level()
314
+ logger.setLevel(log_level)
315
+ datasets.utils.logging.set_verbosity(log_level)
316
+ transformers.utils.logging.set_verbosity(log_level)
317
+ transformers.utils.logging.enable_default_handler()
318
+ transformers.utils.logging.enable_explicit_format()
319
+
320
+ logger.setLevel(logging.INFO if is_main_process(training_args.local_rank) else logging.WARN)
321
+
322
+ # Log on each process the small summary:
323
+ logger.warning(
324
+ f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
325
+ f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
326
+ )
327
+ logger.info(f"Training/evaluation parameters {training_args}")
328
+
329
+ # Set the verbosity to info of the Transformers logger (on main process only):
330
+ if is_main_process(training_args.local_rank):
331
+ transformers.utils.logging.set_verbosity_info()
332
+ logger.info("Training/evaluation parameters %s", training_args)
333
+
334
+ # 3. Detecting last checkpoint and eventually continue from last checkpoint
335
+ last_checkpoint = None
336
+ if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
337
+ last_checkpoint = get_last_checkpoint(training_args.output_dir)
338
+ if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
339
+ raise ValueError(
340
+ f"Output directory ({training_args.output_dir}) already exists and is not empty. "
341
+ "Use --overwrite_output_dir to overcome."
342
+ )
343
+ elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
344
+ logger.info(
345
+ f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
346
+ "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
347
+ )
348
+
349
+ # Set seed before initializing model.
350
+ set_seed(training_args.seed)
351
+
352
+ # 4. Load dataset
353
+ raw_datasets = IterableDatasetDict() if data_args.streaming else DatasetDict()
354
+
355
+ if training_args.do_train:
356
+ raw_datasets["train"] = load_maybe_streaming_dataset(
357
+ data_args.dataset_name,
358
+ data_args.dataset_config_name,
359
+ split=data_args.train_split_name,
360
+ use_auth_token=True if model_args.use_auth_token else None,
361
+ streaming=data_args.streaming,
362
+ )
363
+
364
+ if training_args.do_eval:
365
+ raw_datasets["eval"] = load_maybe_streaming_dataset(
366
+ data_args.dataset_name,
367
+ data_args.dataset_config_name,
368
+ split=data_args.eval_split_name,
369
+ use_auth_token=True if model_args.use_auth_token else None,
370
+ streaming=data_args.streaming,
371
+ )
372
+
373
+ raw_datasets_features = list(next(iter(raw_datasets.values())).features.keys())
374
+
375
+ if data_args.audio_column_name not in raw_datasets_features:
376
+ raise ValueError(
377
+ f"--audio_column_name '{data_args.audio_column_name}' not found in dataset '{data_args.dataset_name}'. "
378
+ "Make sure to set `--audio_column_name` to the correct audio column - one of "
379
+ f"{', '.join(raw_datasets_features)}."
380
+ )
381
+
382
+ if data_args.text_column_name not in raw_datasets_features:
383
+ raise ValueError(
384
+ f"--text_column_name {data_args.text_column_name} not found in dataset '{data_args.dataset_name}'. "
385
+ "Make sure to set `--text_column_name` to the correct text column - one of "
386
+ f"{', '.join(raw_datasets_features)}."
387
+ )
388
+
389
+ # 5. Load pretrained model, tokenizer, and feature extractor
390
+ #
391
+ # Distributed training:
392
+ # The .from_pretrained methods guarantee that only one local process can concurrently
393
+ config = AutoConfig.from_pretrained(
394
+ model_args.config_name if model_args.config_name else model_args.model_name_or_path,
395
+ cache_dir=model_args.cache_dir,
396
+ revision=model_args.model_revision,
397
+ use_auth_token=True if model_args.use_auth_token else None,
398
+ )
399
+
400
+ config.update({"forced_decoder_ids": model_args.forced_decoder_ids, "suppress_tokens": model_args.suppress_tokens})
401
+
402
+ if training_args.gradient_checkpointing:
403
+ config.update({"use_cache": False})
404
+
405
+ feature_extractor = AutoFeatureExtractor.from_pretrained(
406
+ model_args.feature_extractor_name if model_args.feature_extractor_name else model_args.model_name_or_path,
407
+ cache_dir=model_args.cache_dir,
408
+ revision=model_args.model_revision,
409
+ use_auth_token=True if model_args.use_auth_token else None,
410
+ )
411
+ tokenizer = AutoTokenizer.from_pretrained(
412
+ model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
413
+ cache_dir=model_args.cache_dir,
414
+ use_fast=model_args.use_fast_tokenizer,
415
+ revision=model_args.model_revision,
416
+ use_auth_token=True if model_args.use_auth_token else None,
417
+ )
418
+ model = AutoModelForSpeechSeq2Seq.from_pretrained(
419
+ model_args.model_name_or_path,
420
+ config=config,
421
+ cache_dir=model_args.cache_dir,
422
+ revision=model_args.model_revision,
423
+ use_auth_token=True if model_args.use_auth_token else None,
424
+ )
425
+
426
+ if model.config.decoder_start_token_id is None:
427
+ raise ValueError("Make sure that `config.decoder_start_token_id` is correctly defined")
428
+
429
+ if model_args.freeze_feature_encoder:
430
+ model.freeze_feature_encoder()
431
+
432
+ if model_args.freeze_encoder:
433
+ model.freeze_encoder()
434
+
435
+ if data_args.language is not None:
436
+ # We only need to set the task id when the language is specified (i.e. in a multilingual setting)
437
+ tokenizer.set_prefix_tokens(language=data_args.language, task=data_args.task)
438
+
439
+ # 6. Resample speech dataset if necessary
440
+ dataset_sampling_rate = next(iter(raw_datasets.values())).features[data_args.audio_column_name].sampling_rate
441
+ if dataset_sampling_rate != feature_extractor.sampling_rate:
442
+ raw_datasets = raw_datasets.cast_column(
443
+ data_args.audio_column_name, datasets.features.Audio(sampling_rate=feature_extractor.sampling_rate)
444
+ )
445
+
446
+ # 7. Preprocessing the datasets.
447
+ # We need to read the audio files as arrays and tokenize the targets.
448
+ max_input_length = data_args.max_duration_in_seconds * feature_extractor.sampling_rate
449
+ min_input_length = data_args.min_duration_in_seconds * feature_extractor.sampling_rate
450
+ audio_column_name = data_args.audio_column_name
451
+ text_column_name = data_args.text_column_name
452
+ model_input_name = feature_extractor.model_input_names[0]
453
+ do_lower_case = data_args.do_lower_case
454
+ do_remove_punctuation = data_args.do_remove_punctuation
455
+ normalizer = BasicTextNormalizer() # 'official' text normalizer from OpenAI
456
+
457
+ if data_args.max_train_samples is not None:
458
+ raw_datasets["train"] = (
459
+ raw_datasets["train"].take(data_args.max_train_samples)
460
+ if data_args.streaming
461
+ else raw_datasets["train"].select(range(data_args.max_train_samples))
462
+ )
463
+
464
+ if data_args.max_eval_samples is not None:
465
+ raw_datasets["eval"] = (
466
+ raw_datasets["eval"].take(data_args.max_eval_samples)
467
+ if data_args.streaming
468
+ else raw_datasets["eval"].select(range(data_args.max_eval_samples))
469
+ )
470
+
471
+ def prepare_dataset(batch):
472
+ # process audio
473
+ sample = batch[audio_column_name]
474
+ inputs = feature_extractor(sample["array"], sampling_rate=sample["sampling_rate"])
475
+ # process audio length
476
+ batch[model_input_name] = inputs.get(model_input_name)[0]
477
+ batch["input_length"] = len(sample["array"])
478
+
479
+ # process targets
480
+ input_str = batch[text_column_name].lower() if do_lower_case else batch[text_column_name]
481
+ if do_remove_punctuation:
482
+ input_str = normalizer(input_str).strip()
483
+ batch["labels"] = tokenizer(input_str).input_ids
484
+ return batch
485
+
486
+ with training_args.main_process_first(desc="dataset map pre-processing"):
487
+ vectorized_datasets = raw_datasets.map(
488
+ prepare_dataset,
489
+ remove_columns=raw_datasets_features,
490
+ ).with_format("torch")
491
+
492
+ if training_args.do_train and data_args.streaming:
493
+ # manually shuffle if streaming (done by the trainer for non-streaming)
494
+ vectorized_datasets["train"] = vectorized_datasets["train"].shuffle(
495
+ buffer_size=data_args.shuffle_buffer_size,
496
+ seed=training_args.seed,
497
+ )
498
+
499
+ # filter training data that is shorter than min_input_length or longer than
500
+ # max_input_length
501
+ def is_audio_in_length_range(length):
502
+ return min_input_length < length < max_input_length
503
+
504
+ max_label_length = model.config.max_length
505
+ def filter_labels(labels):
506
+ """Filter label sequences longer than max length"""
507
+ return len(labels) < max_label_length
508
+
509
+ vectorized_datasets = vectorized_datasets.filter(filter_labels, input_columns=["labels"])
510
+
511
+ if training_args.do_train:
512
+ vectorized_datasets["train"] = vectorized_datasets["train"].filter(
513
+ is_audio_in_length_range,
514
+ input_columns=["input_length"],
515
+ )
516
+
517
+ # 8. Load Metric
518
+ metric = evaluate.load("wer")
519
+ do_normalize_eval = data_args.do_normalize_eval
520
+
521
+ def compute_metrics(pred):
522
+ pred_ids = pred.predictions
523
+
524
+ pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
525
+
526
+ pred_str = tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
527
+ # we do not want to group tokens when computing the metrics
528
+ label_str = tokenizer.batch_decode(pred.label_ids, skip_special_tokens=True)
529
+
530
+ if do_normalize_eval:
531
+ pred_str = [normalizer(pred) for pred in pred_str]
532
+ label_str = [normalizer(label) for label in label_str]
533
+ # filtering step to only evaluate the samples that correspond to non-zero references:
534
+ pred_str = [pred_str[i] for i in range(len(pred_str)) if len(label_str[i]) > 0]
535
+ label_str = [label_str[i] for i in range(len(label_str)) if len(label_str[i]) > 0]
536
+
537
+ wer = 100 * metric.compute(predictions=pred_str, references=label_str)
538
+
539
+ return {"wer": wer}
540
+
541
+ # 9. Create a single speech processor
542
+ if is_main_process(training_args.local_rank):
543
+ # save feature extractor, tokenizer and config
544
+ feature_extractor.save_pretrained(training_args.output_dir)
545
+ tokenizer.save_pretrained(training_args.output_dir)
546
+ config.save_pretrained(training_args.output_dir)
547
+
548
+ processor = AutoProcessor.from_pretrained(training_args.output_dir)
549
+
550
+ # 10. Define data collator
551
+ data_collator = DataCollatorSpeechSeq2SeqWithPadding(
552
+ processor=processor,
553
+ decoder_start_token_id=model.config.decoder_start_token_id,
554
+ )
555
+
556
+ # 11. Configure Trainer
557
+ # Trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch
558
+ # Only required for streaming: Trainer automatically shuffles non-streaming datasets
559
+ class ShuffleCallback(TrainerCallback):
560
+ def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):
561
+ if isinstance(train_dataloader.dataset, IterableDatasetShard):
562
+ pass # set_epoch() is handled by the Trainer
563
+ elif isinstance(train_dataloader.dataset, IterableDataset):
564
+ train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)
565
+
566
+ # Initialize Trainer
567
+ trainer = Seq2SeqTrainer(
568
+ model=model,
569
+ args=training_args,
570
+ train_dataset=vectorized_datasets["train"] if training_args.do_train else None,
571
+ eval_dataset=vectorized_datasets["eval"] if training_args.do_eval else None,
572
+ tokenizer=feature_extractor,
573
+ data_collator=data_collator,
574
+ compute_metrics=compute_metrics if training_args.predict_with_generate else None,
575
+ callbacks=[ShuffleCallback()] if data_args.streaming else None,
576
+ )
577
+
578
+ # 12. Training
579
+ if training_args.do_train:
580
+ checkpoint = None
581
+ if training_args.resume_from_checkpoint is not None:
582
+ checkpoint = training_args.resume_from_checkpoint
583
+ elif last_checkpoint is not None:
584
+ checkpoint = last_checkpoint
585
+ train_result = trainer.train(resume_from_checkpoint=checkpoint)
586
+ trainer.save_model() # Saves the feature extractor too for easy upload
587
+
588
+ metrics = train_result.metrics
589
+ if data_args.max_train_samples:
590
+ metrics["train_samples"] = data_args.max_train_samples
591
+ trainer.log_metrics("train", metrics)
592
+ trainer.save_metrics("train", metrics)
593
+ trainer.save_state()
594
+
595
+ # 13. Evaluation
596
+ results = {}
597
+ if training_args.do_eval:
598
+ logger.info("*** Evaluate ***")
599
+ metrics = trainer.evaluate(
600
+ metric_key_prefix="eval",
601
+ max_length=training_args.generation_max_length,
602
+ num_beams=training_args.generation_num_beams,
603
+ )
604
+ if data_args.max_eval_samples:
605
+ metrics["eval_samples"] = data_args.max_eval_samples
606
+
607
+ trainer.log_metrics("eval", metrics)
608
+ trainer.save_metrics("eval", metrics)
609
+
610
+ # 14. Write Training Stats
611
+ kwargs = {
612
+ "finetuned_from": model_args.model_name_or_path,
613
+ "tasks": "automatic-speech-recognition",
614
+ "tags": "whisper-event",
615
+ }
616
+ if data_args.dataset_name is not None:
617
+ kwargs["dataset_tags"] = data_args.dataset_name
618
+ if data_args.dataset_config_name is not None:
619
+ kwargs["dataset"] = f"{data_args.dataset_name} {data_args.dataset_config_name}"
620
+ else:
621
+ kwargs["dataset"] = data_args.dataset_name
622
+ if "common_voice" in data_args.dataset_name:
623
+ kwargs["language"] = data_args.dataset_config_name.split('-')[0]
624
+ if model_args.model_index_name is not None:
625
+ kwargs["model_name"] = model_args.model_index_name
626
+
627
+ if training_args.push_to_hub:
628
+ trainer.push_to_hub(**kwargs)
629
+ else:
630
+ trainer.create_model_card(**kwargs)
631
+
632
+ return results
633
+
634
+
635
+ if __name__ == "__main__":
636
+ main()
runs/Jan25_14-33-42_ip-172-31-68-44/events.out.tfevents.1706194391.ip-172-31-68-44.931.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f803040a26e4db40cd6c49b67f13c7955b92d67dece9fb7e84ae7fed962abc
3
+ size 12378
runs/Jan25_14-33-42_ip-172-31-68-44/events.out.tfevents.1706203336.ip-172-31-68-44.931.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6e1ca98e71da4c2aefbee868c749223dc346cef667194083eaae60fee8f99e
3
+ size 406
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2362fd4ebe37709e594d8e77321db7cfea0c7f51a56c880dd8a2de9ca68ebb1
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|en|>",
6
+ "<|zh|>",
7
+ "<|de|>",
8
+ "<|es|>",
9
+ "<|ru|>",
10
+ "<|ko|>",
11
+ "<|fr|>",
12
+ "<|ja|>",
13
+ "<|pt|>",
14
+ "<|tr|>",
15
+ "<|pl|>",
16
+ "<|ca|>",
17
+ "<|nl|>",
18
+ "<|ar|>",
19
+ "<|sv|>",
20
+ "<|it|>",
21
+ "<|id|>",
22
+ "<|hi|>",
23
+ "<|fi|>",
24
+ "<|vi|>",
25
+ "<|he|>",
26
+ "<|uk|>",
27
+ "<|el|>",
28
+ "<|ms|>",
29
+ "<|cs|>",
30
+ "<|ro|>",
31
+ "<|da|>",
32
+ "<|hu|>",
33
+ "<|ta|>",
34
+ "<|no|>",
35
+ "<|th|>",
36
+ "<|ur|>",
37
+ "<|hr|>",
38
+ "<|bg|>",
39
+ "<|lt|>",
40
+ "<|la|>",
41
+ "<|mi|>",
42
+ "<|ml|>",
43
+ "<|cy|>",
44
+ "<|sk|>",
45
+ "<|te|>",
46
+ "<|fa|>",
47
+ "<|lv|>",
48
+ "<|bn|>",
49
+ "<|sr|>",
50
+ "<|az|>",
51
+ "<|sl|>",
52
+ "<|kn|>",
53
+ "<|et|>",
54
+ "<|mk|>",
55
+ "<|br|>",
56
+ "<|eu|>",
57
+ "<|is|>",
58
+ "<|hy|>",
59
+ "<|ne|>",
60
+ "<|mn|>",
61
+ "<|bs|>",
62
+ "<|kk|>",
63
+ "<|sq|>",
64
+ "<|sw|>",
65
+ "<|gl|>",
66
+ "<|mr|>",
67
+ "<|pa|>",
68
+ "<|si|>",
69
+ "<|km|>",
70
+ "<|sn|>",
71
+ "<|yo|>",
72
+ "<|so|>",
73
+ "<|af|>",
74
+ "<|oc|>",
75
+ "<|ka|>",
76
+ "<|be|>",
77
+ "<|tg|>",
78
+ "<|sd|>",
79
+ "<|gu|>",
80
+ "<|am|>",
81
+ "<|yi|>",
82
+ "<|lo|>",
83
+ "<|uz|>",
84
+ "<|fo|>",
85
+ "<|ht|>",
86
+ "<|ps|>",
87
+ "<|tk|>",
88
+ "<|nn|>",
89
+ "<|mt|>",
90
+ "<|sa|>",
91
+ "<|lb|>",
92
+ "<|my|>",
93
+ "<|bo|>",
94
+ "<|tl|>",
95
+ "<|mg|>",
96
+ "<|as|>",
97
+ "<|tt|>",
98
+ "<|haw|>",
99
+ "<|ln|>",
100
+ "<|ha|>",
101
+ "<|ba|>",
102
+ "<|jw|>",
103
+ "<|su|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nocaptions|>",
109
+ "<|notimestamps|>"
110
+ ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": {
126
+ "content": "<|endoftext|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
+ "unk_token": {
133
+ "content": "<|endoftext|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ }
139
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.43,
3
+ "train_loss": 0.23807335948944092,
4
+ "train_runtime": 7036.0339,
5
+ "train_samples_per_second": 9.096,
6
+ "train_steps_per_second": 0.142
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,1440 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 30.43676679820676,
3
+ "best_model_checkpoint": "./checkpoint-5500",
4
+ "epoch": 18.867924528301888,
5
+ "eval_steps": 500,
6
+ "global_step": 5500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09,
13
+ "learning_rate": 5e-08,
14
+ "loss": 0.2499,
15
+ "step": 25
16
+ },
17
+ {
18
+ "epoch": 0.17,
19
+ "learning_rate": 1e-07,
20
+ "loss": 0.2433,
21
+ "step": 50
22
+ },
23
+ {
24
+ "epoch": 0.26,
25
+ "learning_rate": 1.5e-07,
26
+ "loss": 0.2512,
27
+ "step": 75
28
+ },
29
+ {
30
+ "epoch": 0.34,
31
+ "learning_rate": 2e-07,
32
+ "loss": 0.2503,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.43,
37
+ "learning_rate": 2.5e-07,
38
+ "loss": 0.2498,
39
+ "step": 125
40
+ },
41
+ {
42
+ "epoch": 0.51,
43
+ "learning_rate": 3e-07,
44
+ "loss": 0.2501,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 0.6,
49
+ "learning_rate": 3.5e-07,
50
+ "loss": 0.2468,
51
+ "step": 175
52
+ },
53
+ {
54
+ "epoch": 0.69,
55
+ "learning_rate": 4e-07,
56
+ "loss": 0.2462,
57
+ "step": 200
58
+ },
59
+ {
60
+ "epoch": 0.77,
61
+ "learning_rate": 4.5e-07,
62
+ "loss": 0.2495,
63
+ "step": 225
64
+ },
65
+ {
66
+ "epoch": 0.86,
67
+ "learning_rate": 5e-07,
68
+ "loss": 0.2472,
69
+ "step": 250
70
+ },
71
+ {
72
+ "epoch": 0.94,
73
+ "learning_rate": 5.5e-07,
74
+ "loss": 0.2449,
75
+ "step": 275
76
+ },
77
+ {
78
+ "epoch": 1.03,
79
+ "learning_rate": 6e-07,
80
+ "loss": 0.2475,
81
+ "step": 300
82
+ },
83
+ {
84
+ "epoch": 1.11,
85
+ "learning_rate": 6.5e-07,
86
+ "loss": 0.2452,
87
+ "step": 325
88
+ },
89
+ {
90
+ "epoch": 1.2,
91
+ "learning_rate": 7e-07,
92
+ "loss": 0.2441,
93
+ "step": 350
94
+ },
95
+ {
96
+ "epoch": 1.29,
97
+ "learning_rate": 7.5e-07,
98
+ "loss": 0.2422,
99
+ "step": 375
100
+ },
101
+ {
102
+ "epoch": 1.37,
103
+ "learning_rate": 8e-07,
104
+ "loss": 0.2422,
105
+ "step": 400
106
+ },
107
+ {
108
+ "epoch": 1.46,
109
+ "learning_rate": 8.499999999999999e-07,
110
+ "loss": 0.2445,
111
+ "step": 425
112
+ },
113
+ {
114
+ "epoch": 1.54,
115
+ "learning_rate": 9e-07,
116
+ "loss": 0.2449,
117
+ "step": 450
118
+ },
119
+ {
120
+ "epoch": 1.63,
121
+ "learning_rate": 9.499999999999999e-07,
122
+ "loss": 0.2442,
123
+ "step": 475
124
+ },
125
+ {
126
+ "epoch": 1.72,
127
+ "learning_rate": 1e-06,
128
+ "loss": 0.2476,
129
+ "step": 500
130
+ },
131
+ {
132
+ "epoch": 1.72,
133
+ "eval_loss": 0.2750862240791321,
134
+ "eval_runtime": 1902.3234,
135
+ "eval_samples_per_second": 4.896,
136
+ "eval_steps_per_second": 0.153,
137
+ "eval_wer": 36.1694988054012,
138
+ "step": 500
139
+ },
140
+ {
141
+ "epoch": 1.8,
142
+ "learning_rate": 9.968749999999999e-07,
143
+ "loss": 0.2424,
144
+ "step": 525
145
+ },
146
+ {
147
+ "epoch": 1.89,
148
+ "learning_rate": 9.9375e-07,
149
+ "loss": 0.2374,
150
+ "step": 550
151
+ },
152
+ {
153
+ "epoch": 1.97,
154
+ "learning_rate": 9.90625e-07,
155
+ "loss": 0.2401,
156
+ "step": 575
157
+ },
158
+ {
159
+ "epoch": 2.06,
160
+ "learning_rate": 9.875e-07,
161
+ "loss": 0.2373,
162
+ "step": 600
163
+ },
164
+ {
165
+ "epoch": 2.14,
166
+ "learning_rate": 9.84375e-07,
167
+ "loss": 0.2344,
168
+ "step": 625
169
+ },
170
+ {
171
+ "epoch": 2.23,
172
+ "learning_rate": 9.8125e-07,
173
+ "loss": 0.2384,
174
+ "step": 650
175
+ },
176
+ {
177
+ "epoch": 2.32,
178
+ "learning_rate": 9.78125e-07,
179
+ "loss": 0.2382,
180
+ "step": 675
181
+ },
182
+ {
183
+ "epoch": 2.4,
184
+ "learning_rate": 9.75e-07,
185
+ "loss": 0.2404,
186
+ "step": 700
187
+ },
188
+ {
189
+ "epoch": 2.49,
190
+ "learning_rate": 9.71875e-07,
191
+ "loss": 0.2312,
192
+ "step": 725
193
+ },
194
+ {
195
+ "epoch": 2.57,
196
+ "learning_rate": 9.6875e-07,
197
+ "loss": 0.2337,
198
+ "step": 750
199
+ },
200
+ {
201
+ "epoch": 2.66,
202
+ "learning_rate": 9.65625e-07,
203
+ "loss": 0.2314,
204
+ "step": 775
205
+ },
206
+ {
207
+ "epoch": 2.74,
208
+ "learning_rate": 9.624999999999999e-07,
209
+ "loss": 0.2262,
210
+ "step": 800
211
+ },
212
+ {
213
+ "epoch": 2.83,
214
+ "learning_rate": 9.59375e-07,
215
+ "loss": 0.2342,
216
+ "step": 825
217
+ },
218
+ {
219
+ "epoch": 2.92,
220
+ "learning_rate": 9.5625e-07,
221
+ "loss": 0.2358,
222
+ "step": 850
223
+ },
224
+ {
225
+ "epoch": 3.0,
226
+ "learning_rate": 9.53125e-07,
227
+ "loss": 0.2316,
228
+ "step": 875
229
+ },
230
+ {
231
+ "epoch": 3.09,
232
+ "learning_rate": 9.499999999999999e-07,
233
+ "loss": 0.2344,
234
+ "step": 900
235
+ },
236
+ {
237
+ "epoch": 3.17,
238
+ "learning_rate": 9.468749999999999e-07,
239
+ "loss": 0.2224,
240
+ "step": 925
241
+ },
242
+ {
243
+ "epoch": 3.26,
244
+ "learning_rate": 9.4375e-07,
245
+ "loss": 0.2219,
246
+ "step": 950
247
+ },
248
+ {
249
+ "epoch": 3.34,
250
+ "learning_rate": 9.40625e-07,
251
+ "loss": 0.2302,
252
+ "step": 975
253
+ },
254
+ {
255
+ "epoch": 3.43,
256
+ "learning_rate": 9.374999999999999e-07,
257
+ "loss": 0.2284,
258
+ "step": 1000
259
+ },
260
+ {
261
+ "epoch": 3.43,
262
+ "eval_loss": 0.26221010088920593,
263
+ "eval_runtime": 1890.4325,
264
+ "eval_samples_per_second": 4.927,
265
+ "eval_steps_per_second": 0.154,
266
+ "eval_wer": 35.16684115862662,
267
+ "step": 1000
268
+ },
269
+ {
270
+ "epoch": 3.52,
271
+ "learning_rate": 9.34375e-07,
272
+ "loss": 0.2283,
273
+ "step": 1025
274
+ },
275
+ {
276
+ "epoch": 3.6,
277
+ "learning_rate": 9.3125e-07,
278
+ "loss": 0.2219,
279
+ "step": 1050
280
+ },
281
+ {
282
+ "epoch": 3.69,
283
+ "learning_rate": 9.281249999999999e-07,
284
+ "loss": 0.2241,
285
+ "step": 1075
286
+ },
287
+ {
288
+ "epoch": 3.77,
289
+ "learning_rate": 9.25e-07,
290
+ "loss": 0.2259,
291
+ "step": 1100
292
+ },
293
+ {
294
+ "epoch": 3.86,
295
+ "learning_rate": 9.21875e-07,
296
+ "loss": 0.2214,
297
+ "step": 1125
298
+ },
299
+ {
300
+ "epoch": 3.95,
301
+ "learning_rate": 9.187499999999999e-07,
302
+ "loss": 0.2217,
303
+ "step": 1150
304
+ },
305
+ {
306
+ "epoch": 4.03,
307
+ "learning_rate": 9.15625e-07,
308
+ "loss": 0.2208,
309
+ "step": 1175
310
+ },
311
+ {
312
+ "epoch": 4.12,
313
+ "learning_rate": 9.124999999999999e-07,
314
+ "loss": 0.2191,
315
+ "step": 1200
316
+ },
317
+ {
318
+ "epoch": 4.2,
319
+ "learning_rate": 9.09375e-07,
320
+ "loss": 0.2163,
321
+ "step": 1225
322
+ },
323
+ {
324
+ "epoch": 4.29,
325
+ "learning_rate": 9.0625e-07,
326
+ "loss": 0.2222,
327
+ "step": 1250
328
+ },
329
+ {
330
+ "epoch": 4.37,
331
+ "learning_rate": 9.031249999999999e-07,
332
+ "loss": 0.2178,
333
+ "step": 1275
334
+ },
335
+ {
336
+ "epoch": 4.46,
337
+ "learning_rate": 9e-07,
338
+ "loss": 0.2179,
339
+ "step": 1300
340
+ },
341
+ {
342
+ "epoch": 4.55,
343
+ "learning_rate": 8.96875e-07,
344
+ "loss": 0.2214,
345
+ "step": 1325
346
+ },
347
+ {
348
+ "epoch": 4.63,
349
+ "learning_rate": 8.9375e-07,
350
+ "loss": 0.2147,
351
+ "step": 1350
352
+ },
353
+ {
354
+ "epoch": 4.72,
355
+ "learning_rate": 8.906249999999999e-07,
356
+ "loss": 0.217,
357
+ "step": 1375
358
+ },
359
+ {
360
+ "epoch": 4.8,
361
+ "learning_rate": 8.874999999999999e-07,
362
+ "loss": 0.2167,
363
+ "step": 1400
364
+ },
365
+ {
366
+ "epoch": 4.89,
367
+ "learning_rate": 8.84375e-07,
368
+ "loss": 0.2188,
369
+ "step": 1425
370
+ },
371
+ {
372
+ "epoch": 4.97,
373
+ "learning_rate": 8.812499999999999e-07,
374
+ "loss": 0.2154,
375
+ "step": 1450
376
+ },
377
+ {
378
+ "epoch": 5.06,
379
+ "learning_rate": 8.78125e-07,
380
+ "loss": 0.2173,
381
+ "step": 1475
382
+ },
383
+ {
384
+ "epoch": 5.15,
385
+ "learning_rate": 8.75e-07,
386
+ "loss": 0.213,
387
+ "step": 1500
388
+ },
389
+ {
390
+ "epoch": 5.15,
391
+ "eval_loss": 0.252381831407547,
392
+ "eval_runtime": 1875.2145,
393
+ "eval_samples_per_second": 4.967,
394
+ "eval_steps_per_second": 0.156,
395
+ "eval_wer": 34.202213810814925,
396
+ "step": 1500
397
+ },
398
+ {
399
+ "epoch": 5.23,
400
+ "learning_rate": 8.718749999999999e-07,
401
+ "loss": 0.2121,
402
+ "step": 1525
403
+ },
404
+ {
405
+ "epoch": 5.32,
406
+ "learning_rate": 8.687499999999999e-07,
407
+ "loss": 0.2112,
408
+ "step": 1550
409
+ },
410
+ {
411
+ "epoch": 5.4,
412
+ "learning_rate": 8.65625e-07,
413
+ "loss": 0.2109,
414
+ "step": 1575
415
+ },
416
+ {
417
+ "epoch": 5.49,
418
+ "learning_rate": 8.625e-07,
419
+ "loss": 0.2106,
420
+ "step": 1600
421
+ },
422
+ {
423
+ "epoch": 5.57,
424
+ "learning_rate": 8.593749999999999e-07,
425
+ "loss": 0.2081,
426
+ "step": 1625
427
+ },
428
+ {
429
+ "epoch": 5.66,
430
+ "learning_rate": 8.5625e-07,
431
+ "loss": 0.2122,
432
+ "step": 1650
433
+ },
434
+ {
435
+ "epoch": 5.75,
436
+ "learning_rate": 8.53125e-07,
437
+ "loss": 0.211,
438
+ "step": 1675
439
+ },
440
+ {
441
+ "epoch": 5.83,
442
+ "learning_rate": 8.499999999999999e-07,
443
+ "loss": 0.2072,
444
+ "step": 1700
445
+ },
446
+ {
447
+ "epoch": 5.92,
448
+ "learning_rate": 8.46875e-07,
449
+ "loss": 0.2063,
450
+ "step": 1725
451
+ },
452
+ {
453
+ "epoch": 6.0,
454
+ "learning_rate": 8.4375e-07,
455
+ "loss": 0.2137,
456
+ "step": 1750
457
+ },
458
+ {
459
+ "epoch": 6.09,
460
+ "learning_rate": 8.406249999999999e-07,
461
+ "loss": 0.2095,
462
+ "step": 1775
463
+ },
464
+ {
465
+ "epoch": 6.17,
466
+ "learning_rate": 8.375e-07,
467
+ "loss": 0.2096,
468
+ "step": 1800
469
+ },
470
+ {
471
+ "epoch": 6.26,
472
+ "learning_rate": 8.34375e-07,
473
+ "loss": 0.2087,
474
+ "step": 1825
475
+ },
476
+ {
477
+ "epoch": 6.35,
478
+ "learning_rate": 8.3125e-07,
479
+ "loss": 0.2021,
480
+ "step": 1850
481
+ },
482
+ {
483
+ "epoch": 6.43,
484
+ "learning_rate": 8.28125e-07,
485
+ "loss": 0.2076,
486
+ "step": 1875
487
+ },
488
+ {
489
+ "epoch": 6.52,
490
+ "learning_rate": 8.249999999999999e-07,
491
+ "loss": 0.2024,
492
+ "step": 1900
493
+ },
494
+ {
495
+ "epoch": 6.6,
496
+ "learning_rate": 8.21875e-07,
497
+ "loss": 0.2013,
498
+ "step": 1925
499
+ },
500
+ {
501
+ "epoch": 6.69,
502
+ "learning_rate": 8.187499999999999e-07,
503
+ "loss": 0.2043,
504
+ "step": 1950
505
+ },
506
+ {
507
+ "epoch": 6.78,
508
+ "learning_rate": 8.15625e-07,
509
+ "loss": 0.1991,
510
+ "step": 1975
511
+ },
512
+ {
513
+ "epoch": 6.86,
514
+ "learning_rate": 8.125e-07,
515
+ "loss": 0.2048,
516
+ "step": 2000
517
+ },
518
+ {
519
+ "epoch": 6.86,
520
+ "eval_loss": 0.2446550577878952,
521
+ "eval_runtime": 1880.3132,
522
+ "eval_samples_per_second": 4.953,
523
+ "eval_steps_per_second": 0.155,
524
+ "eval_wer": 33.52661673512121,
525
+ "step": 2000
526
+ },
527
+ {
528
+ "epoch": 6.95,
529
+ "learning_rate": 8.093749999999999e-07,
530
+ "loss": 0.2022,
531
+ "step": 2025
532
+ },
533
+ {
534
+ "epoch": 7.03,
535
+ "learning_rate": 8.0625e-07,
536
+ "loss": 0.208,
537
+ "step": 2050
538
+ },
539
+ {
540
+ "epoch": 7.12,
541
+ "learning_rate": 8.031249999999999e-07,
542
+ "loss": 0.2016,
543
+ "step": 2075
544
+ },
545
+ {
546
+ "epoch": 7.2,
547
+ "learning_rate": 8e-07,
548
+ "loss": 0.1955,
549
+ "step": 2100
550
+ },
551
+ {
552
+ "epoch": 7.29,
553
+ "learning_rate": 7.96875e-07,
554
+ "loss": 0.2013,
555
+ "step": 2125
556
+ },
557
+ {
558
+ "epoch": 7.38,
559
+ "learning_rate": 7.937499999999999e-07,
560
+ "loss": 0.1993,
561
+ "step": 2150
562
+ },
563
+ {
564
+ "epoch": 7.46,
565
+ "learning_rate": 7.90625e-07,
566
+ "loss": 0.201,
567
+ "step": 2175
568
+ },
569
+ {
570
+ "epoch": 7.55,
571
+ "learning_rate": 7.875e-07,
572
+ "loss": 0.1976,
573
+ "step": 2200
574
+ },
575
+ {
576
+ "epoch": 7.63,
577
+ "learning_rate": 7.84375e-07,
578
+ "loss": 0.194,
579
+ "step": 2225
580
+ },
581
+ {
582
+ "epoch": 7.72,
583
+ "learning_rate": 7.812499999999999e-07,
584
+ "loss": 0.1999,
585
+ "step": 2250
586
+ },
587
+ {
588
+ "epoch": 7.8,
589
+ "learning_rate": 7.78125e-07,
590
+ "loss": 0.1991,
591
+ "step": 2275
592
+ },
593
+ {
594
+ "epoch": 7.89,
595
+ "learning_rate": 7.75e-07,
596
+ "loss": 0.2026,
597
+ "step": 2300
598
+ },
599
+ {
600
+ "epoch": 7.98,
601
+ "learning_rate": 7.718749999999999e-07,
602
+ "loss": 0.1987,
603
+ "step": 2325
604
+ },
605
+ {
606
+ "epoch": 8.06,
607
+ "learning_rate": 7.688749999999999e-07,
608
+ "loss": 0.1996,
609
+ "step": 2350
610
+ },
611
+ {
612
+ "epoch": 8.15,
613
+ "learning_rate": 7.6575e-07,
614
+ "loss": 0.1903,
615
+ "step": 2375
616
+ },
617
+ {
618
+ "epoch": 8.23,
619
+ "learning_rate": 7.62625e-07,
620
+ "loss": 0.1945,
621
+ "step": 2400
622
+ },
623
+ {
624
+ "epoch": 8.32,
625
+ "learning_rate": 7.594999999999999e-07,
626
+ "loss": 0.1972,
627
+ "step": 2425
628
+ },
629
+ {
630
+ "epoch": 8.4,
631
+ "learning_rate": 7.56375e-07,
632
+ "loss": 0.1971,
633
+ "step": 2450
634
+ },
635
+ {
636
+ "epoch": 8.49,
637
+ "learning_rate": 7.532499999999999e-07,
638
+ "loss": 0.1988,
639
+ "step": 2475
640
+ },
641
+ {
642
+ "epoch": 8.58,
643
+ "learning_rate": 7.50125e-07,
644
+ "loss": 0.1948,
645
+ "step": 2500
646
+ },
647
+ {
648
+ "epoch": 8.58,
649
+ "eval_loss": 0.2382451444864273,
650
+ "eval_runtime": 1871.3425,
651
+ "eval_samples_per_second": 4.977,
652
+ "eval_steps_per_second": 0.156,
653
+ "eval_wer": 32.74945639043247,
654
+ "step": 2500
655
+ },
656
+ {
657
+ "epoch": 8.66,
658
+ "learning_rate": 7.47e-07,
659
+ "loss": 0.1951,
660
+ "step": 2525
661
+ },
662
+ {
663
+ "epoch": 8.75,
664
+ "learning_rate": 7.438749999999999e-07,
665
+ "loss": 0.1897,
666
+ "step": 2550
667
+ },
668
+ {
669
+ "epoch": 8.83,
670
+ "learning_rate": 7.4075e-07,
671
+ "loss": 0.1887,
672
+ "step": 2575
673
+ },
674
+ {
675
+ "epoch": 8.92,
676
+ "learning_rate": 7.37625e-07,
677
+ "loss": 0.1966,
678
+ "step": 2600
679
+ },
680
+ {
681
+ "epoch": 9.01,
682
+ "learning_rate": 7.345e-07,
683
+ "loss": 0.1936,
684
+ "step": 2625
685
+ },
686
+ {
687
+ "epoch": 9.09,
688
+ "learning_rate": 7.313749999999999e-07,
689
+ "loss": 0.1939,
690
+ "step": 2650
691
+ },
692
+ {
693
+ "epoch": 9.18,
694
+ "learning_rate": 7.282499999999999e-07,
695
+ "loss": 0.1931,
696
+ "step": 2675
697
+ },
698
+ {
699
+ "epoch": 9.26,
700
+ "learning_rate": 7.25125e-07,
701
+ "loss": 0.1903,
702
+ "step": 2700
703
+ },
704
+ {
705
+ "epoch": 9.35,
706
+ "learning_rate": 7.219999999999999e-07,
707
+ "loss": 0.1852,
708
+ "step": 2725
709
+ },
710
+ {
711
+ "epoch": 9.43,
712
+ "learning_rate": 7.18875e-07,
713
+ "loss": 0.1916,
714
+ "step": 2750
715
+ },
716
+ {
717
+ "epoch": 9.52,
718
+ "learning_rate": 7.1575e-07,
719
+ "loss": 0.1882,
720
+ "step": 2775
721
+ },
722
+ {
723
+ "epoch": 9.61,
724
+ "learning_rate": 7.126249999999999e-07,
725
+ "loss": 0.1872,
726
+ "step": 2800
727
+ },
728
+ {
729
+ "epoch": 9.69,
730
+ "learning_rate": 7.094999999999999e-07,
731
+ "loss": 0.1915,
732
+ "step": 2825
733
+ },
734
+ {
735
+ "epoch": 9.78,
736
+ "learning_rate": 7.06375e-07,
737
+ "loss": 0.191,
738
+ "step": 2850
739
+ },
740
+ {
741
+ "epoch": 9.86,
742
+ "learning_rate": 7.0325e-07,
743
+ "loss": 0.1873,
744
+ "step": 2875
745
+ },
746
+ {
747
+ "epoch": 9.95,
748
+ "learning_rate": 7.001249999999999e-07,
749
+ "loss": 0.192,
750
+ "step": 2900
751
+ },
752
+ {
753
+ "epoch": 10.03,
754
+ "learning_rate": 6.97e-07,
755
+ "loss": 0.1874,
756
+ "step": 2925
757
+ },
758
+ {
759
+ "epoch": 10.12,
760
+ "learning_rate": 6.93875e-07,
761
+ "loss": 0.1803,
762
+ "step": 2950
763
+ },
764
+ {
765
+ "epoch": 10.21,
766
+ "learning_rate": 6.907499999999999e-07,
767
+ "loss": 0.1874,
768
+ "step": 2975
769
+ },
770
+ {
771
+ "epoch": 10.29,
772
+ "learning_rate": 6.87625e-07,
773
+ "loss": 0.1852,
774
+ "step": 3000
775
+ },
776
+ {
777
+ "epoch": 10.29,
778
+ "eval_loss": 0.2334369719028473,
779
+ "eval_runtime": 1876.9245,
780
+ "eval_samples_per_second": 4.962,
781
+ "eval_steps_per_second": 0.156,
782
+ "eval_wer": 32.23224432453715,
783
+ "step": 3000
784
+ },
785
+ {
786
+ "epoch": 10.38,
787
+ "learning_rate": 6.845e-07,
788
+ "loss": 0.1835,
789
+ "step": 3025
790
+ },
791
+ {
792
+ "epoch": 10.46,
793
+ "learning_rate": 6.813749999999999e-07,
794
+ "loss": 0.1887,
795
+ "step": 3050
796
+ },
797
+ {
798
+ "epoch": 10.55,
799
+ "learning_rate": 6.7825e-07,
800
+ "loss": 0.1837,
801
+ "step": 3075
802
+ },
803
+ {
804
+ "epoch": 10.63,
805
+ "learning_rate": 6.75125e-07,
806
+ "loss": 0.1831,
807
+ "step": 3100
808
+ },
809
+ {
810
+ "epoch": 10.72,
811
+ "learning_rate": 6.72e-07,
812
+ "loss": 0.1879,
813
+ "step": 3125
814
+ },
815
+ {
816
+ "epoch": 10.81,
817
+ "learning_rate": 6.68875e-07,
818
+ "loss": 0.1852,
819
+ "step": 3150
820
+ },
821
+ {
822
+ "epoch": 10.89,
823
+ "learning_rate": 6.657499999999999e-07,
824
+ "loss": 0.1908,
825
+ "step": 3175
826
+ },
827
+ {
828
+ "epoch": 10.98,
829
+ "learning_rate": 6.62625e-07,
830
+ "loss": 0.1892,
831
+ "step": 3200
832
+ },
833
+ {
834
+ "epoch": 11.06,
835
+ "learning_rate": 6.595e-07,
836
+ "loss": 0.1819,
837
+ "step": 3225
838
+ },
839
+ {
840
+ "epoch": 11.15,
841
+ "learning_rate": 6.56375e-07,
842
+ "loss": 0.1827,
843
+ "step": 3250
844
+ },
845
+ {
846
+ "epoch": 11.23,
847
+ "learning_rate": 6.5325e-07,
848
+ "loss": 0.1814,
849
+ "step": 3275
850
+ },
851
+ {
852
+ "epoch": 11.32,
853
+ "learning_rate": 6.501249999999999e-07,
854
+ "loss": 0.1789,
855
+ "step": 3300
856
+ },
857
+ {
858
+ "epoch": 11.41,
859
+ "learning_rate": 6.47e-07,
860
+ "loss": 0.1778,
861
+ "step": 3325
862
+ },
863
+ {
864
+ "epoch": 11.49,
865
+ "learning_rate": 6.438749999999999e-07,
866
+ "loss": 0.1814,
867
+ "step": 3350
868
+ },
869
+ {
870
+ "epoch": 11.58,
871
+ "learning_rate": 6.4075e-07,
872
+ "loss": 0.1875,
873
+ "step": 3375
874
+ },
875
+ {
876
+ "epoch": 11.66,
877
+ "learning_rate": 6.37625e-07,
878
+ "loss": 0.1886,
879
+ "step": 3400
880
+ },
881
+ {
882
+ "epoch": 11.75,
883
+ "learning_rate": 6.344999999999999e-07,
884
+ "loss": 0.1816,
885
+ "step": 3425
886
+ },
887
+ {
888
+ "epoch": 11.84,
889
+ "learning_rate": 6.31375e-07,
890
+ "loss": 0.1822,
891
+ "step": 3450
892
+ },
893
+ {
894
+ "epoch": 11.92,
895
+ "learning_rate": 6.2825e-07,
896
+ "loss": 0.1798,
897
+ "step": 3475
898
+ },
899
+ {
900
+ "epoch": 12.01,
901
+ "learning_rate": 6.25125e-07,
902
+ "loss": 0.1789,
903
+ "step": 3500
904
+ },
905
+ {
906
+ "epoch": 12.01,
907
+ "eval_loss": 0.22954809665679932,
908
+ "eval_runtime": 1876.8523,
909
+ "eval_samples_per_second": 4.963,
910
+ "eval_steps_per_second": 0.156,
911
+ "eval_wer": 31.72442797956207,
912
+ "step": 3500
913
+ },
914
+ {
915
+ "epoch": 12.09,
916
+ "learning_rate": 6.219999999999999e-07,
917
+ "loss": 0.1792,
918
+ "step": 3525
919
+ },
920
+ {
921
+ "epoch": 12.18,
922
+ "learning_rate": 6.18875e-07,
923
+ "loss": 0.1805,
924
+ "step": 3550
925
+ },
926
+ {
927
+ "epoch": 12.26,
928
+ "learning_rate": 6.1575e-07,
929
+ "loss": 0.1803,
930
+ "step": 3575
931
+ },
932
+ {
933
+ "epoch": 12.35,
934
+ "learning_rate": 6.126249999999999e-07,
935
+ "loss": 0.1808,
936
+ "step": 3600
937
+ },
938
+ {
939
+ "epoch": 12.44,
940
+ "learning_rate": 6.095e-07,
941
+ "loss": 0.1789,
942
+ "step": 3625
943
+ },
944
+ {
945
+ "epoch": 12.52,
946
+ "learning_rate": 6.06375e-07,
947
+ "loss": 0.178,
948
+ "step": 3650
949
+ },
950
+ {
951
+ "epoch": 12.61,
952
+ "learning_rate": 6.032499999999999e-07,
953
+ "loss": 0.1808,
954
+ "step": 3675
955
+ },
956
+ {
957
+ "epoch": 12.69,
958
+ "learning_rate": 6.00125e-07,
959
+ "loss": 0.1766,
960
+ "step": 3700
961
+ },
962
+ {
963
+ "epoch": 12.78,
964
+ "learning_rate": 5.97e-07,
965
+ "loss": 0.176,
966
+ "step": 3725
967
+ },
968
+ {
969
+ "epoch": 12.86,
970
+ "learning_rate": 5.93875e-07,
971
+ "loss": 0.1804,
972
+ "step": 3750
973
+ },
974
+ {
975
+ "epoch": 12.95,
976
+ "learning_rate": 5.9075e-07,
977
+ "loss": 0.1758,
978
+ "step": 3775
979
+ },
980
+ {
981
+ "epoch": 13.04,
982
+ "learning_rate": 5.876249999999999e-07,
983
+ "loss": 0.1754,
984
+ "step": 3800
985
+ },
986
+ {
987
+ "epoch": 13.12,
988
+ "learning_rate": 5.845e-07,
989
+ "loss": 0.1783,
990
+ "step": 3825
991
+ },
992
+ {
993
+ "epoch": 13.21,
994
+ "learning_rate": 5.813749999999999e-07,
995
+ "loss": 0.1763,
996
+ "step": 3850
997
+ },
998
+ {
999
+ "epoch": 13.29,
1000
+ "learning_rate": 5.7825e-07,
1001
+ "loss": 0.1768,
1002
+ "step": 3875
1003
+ },
1004
+ {
1005
+ "epoch": 13.38,
1006
+ "learning_rate": 5.75125e-07,
1007
+ "loss": 0.1724,
1008
+ "step": 3900
1009
+ },
1010
+ {
1011
+ "epoch": 13.46,
1012
+ "learning_rate": 5.719999999999999e-07,
1013
+ "loss": 0.1776,
1014
+ "step": 3925
1015
+ },
1016
+ {
1017
+ "epoch": 13.55,
1018
+ "learning_rate": 5.68875e-07,
1019
+ "loss": 0.1742,
1020
+ "step": 3950
1021
+ },
1022
+ {
1023
+ "epoch": 13.64,
1024
+ "learning_rate": 5.657499999999999e-07,
1025
+ "loss": 0.1732,
1026
+ "step": 3975
1027
+ },
1028
+ {
1029
+ "epoch": 13.72,
1030
+ "learning_rate": 5.62625e-07,
1031
+ "loss": 0.1738,
1032
+ "step": 4000
1033
+ },
1034
+ {
1035
+ "epoch": 13.72,
1036
+ "eval_loss": 0.2260207086801529,
1037
+ "eval_runtime": 1879.4952,
1038
+ "eval_samples_per_second": 4.956,
1039
+ "eval_steps_per_second": 0.155,
1040
+ "eval_wer": 31.23406083058173,
1041
+ "step": 4000
1042
+ },
1043
+ {
1044
+ "epoch": 13.81,
1045
+ "learning_rate": 5.595e-07,
1046
+ "loss": 0.1756,
1047
+ "step": 4025
1048
+ },
1049
+ {
1050
+ "epoch": 13.89,
1051
+ "learning_rate": 5.563749999999999e-07,
1052
+ "loss": 0.1778,
1053
+ "step": 4050
1054
+ },
1055
+ {
1056
+ "epoch": 13.98,
1057
+ "learning_rate": 5.5325e-07,
1058
+ "loss": 0.1756,
1059
+ "step": 4075
1060
+ },
1061
+ {
1062
+ "epoch": 14.07,
1063
+ "learning_rate": 5.50125e-07,
1064
+ "loss": 0.1748,
1065
+ "step": 4100
1066
+ },
1067
+ {
1068
+ "epoch": 14.15,
1069
+ "learning_rate": 5.47e-07,
1070
+ "loss": 0.1738,
1071
+ "step": 4125
1072
+ },
1073
+ {
1074
+ "epoch": 14.24,
1075
+ "learning_rate": 5.438749999999999e-07,
1076
+ "loss": 0.1706,
1077
+ "step": 4150
1078
+ },
1079
+ {
1080
+ "epoch": 14.32,
1081
+ "learning_rate": 5.4075e-07,
1082
+ "loss": 0.1764,
1083
+ "step": 4175
1084
+ },
1085
+ {
1086
+ "epoch": 14.41,
1087
+ "learning_rate": 5.37625e-07,
1088
+ "loss": 0.1734,
1089
+ "step": 4200
1090
+ },
1091
+ {
1092
+ "epoch": 14.49,
1093
+ "learning_rate": 5.344999999999999e-07,
1094
+ "loss": 0.1697,
1095
+ "step": 4225
1096
+ },
1097
+ {
1098
+ "epoch": 14.58,
1099
+ "learning_rate": 5.313750000000001e-07,
1100
+ "loss": 0.178,
1101
+ "step": 4250
1102
+ },
1103
+ {
1104
+ "epoch": 14.67,
1105
+ "learning_rate": 5.2825e-07,
1106
+ "loss": 0.1714,
1107
+ "step": 4275
1108
+ },
1109
+ {
1110
+ "epoch": 14.75,
1111
+ "learning_rate": 5.251249999999999e-07,
1112
+ "loss": 0.172,
1113
+ "step": 4300
1114
+ },
1115
+ {
1116
+ "epoch": 14.84,
1117
+ "learning_rate": 5.22e-07,
1118
+ "loss": 0.1714,
1119
+ "step": 4325
1120
+ },
1121
+ {
1122
+ "epoch": 14.92,
1123
+ "learning_rate": 5.18875e-07,
1124
+ "loss": 0.1701,
1125
+ "step": 4350
1126
+ },
1127
+ {
1128
+ "epoch": 15.01,
1129
+ "learning_rate": 5.15875e-07,
1130
+ "loss": 0.1714,
1131
+ "step": 4375
1132
+ },
1133
+ {
1134
+ "epoch": 15.09,
1135
+ "learning_rate": 5.1275e-07,
1136
+ "loss": 0.17,
1137
+ "step": 4400
1138
+ },
1139
+ {
1140
+ "epoch": 15.18,
1141
+ "learning_rate": 5.09625e-07,
1142
+ "loss": 0.1709,
1143
+ "step": 4425
1144
+ },
1145
+ {
1146
+ "epoch": 15.27,
1147
+ "learning_rate": 5.064999999999999e-07,
1148
+ "loss": 0.1742,
1149
+ "step": 4450
1150
+ },
1151
+ {
1152
+ "epoch": 15.35,
1153
+ "learning_rate": 5.03375e-07,
1154
+ "loss": 0.1708,
1155
+ "step": 4475
1156
+ },
1157
+ {
1158
+ "epoch": 15.44,
1159
+ "learning_rate": 5.0025e-07,
1160
+ "loss": 0.166,
1161
+ "step": 4500
1162
+ },
1163
+ {
1164
+ "epoch": 15.44,
1165
+ "eval_loss": 0.2236023247241974,
1166
+ "eval_runtime": 1888.9296,
1167
+ "eval_samples_per_second": 4.931,
1168
+ "eval_steps_per_second": 0.155,
1169
+ "eval_wer": 30.956215940511665,
1170
+ "step": 4500
1171
+ },
1172
+ {
1173
+ "epoch": 15.52,
1174
+ "learning_rate": 4.971249999999999e-07,
1175
+ "loss": 0.1727,
1176
+ "step": 4525
1177
+ },
1178
+ {
1179
+ "epoch": 15.61,
1180
+ "learning_rate": 4.94e-07,
1181
+ "loss": 0.1689,
1182
+ "step": 4550
1183
+ },
1184
+ {
1185
+ "epoch": 15.69,
1186
+ "learning_rate": 4.90875e-07,
1187
+ "loss": 0.1686,
1188
+ "step": 4575
1189
+ },
1190
+ {
1191
+ "epoch": 15.78,
1192
+ "learning_rate": 4.8775e-07,
1193
+ "loss": 0.1733,
1194
+ "step": 4600
1195
+ },
1196
+ {
1197
+ "epoch": 15.87,
1198
+ "learning_rate": 4.846249999999999e-07,
1199
+ "loss": 0.1704,
1200
+ "step": 4625
1201
+ },
1202
+ {
1203
+ "epoch": 15.95,
1204
+ "learning_rate": 4.815e-07,
1205
+ "loss": 0.1681,
1206
+ "step": 4650
1207
+ },
1208
+ {
1209
+ "epoch": 16.04,
1210
+ "learning_rate": 4.78375e-07,
1211
+ "loss": 0.1659,
1212
+ "step": 4675
1213
+ },
1214
+ {
1215
+ "epoch": 16.12,
1216
+ "learning_rate": 4.7524999999999997e-07,
1217
+ "loss": 0.1722,
1218
+ "step": 4700
1219
+ },
1220
+ {
1221
+ "epoch": 16.21,
1222
+ "learning_rate": 4.72125e-07,
1223
+ "loss": 0.1662,
1224
+ "step": 4725
1225
+ },
1226
+ {
1227
+ "epoch": 16.3,
1228
+ "learning_rate": 4.689999999999999e-07,
1229
+ "loss": 0.1679,
1230
+ "step": 4750
1231
+ },
1232
+ {
1233
+ "epoch": 16.38,
1234
+ "learning_rate": 4.6587499999999995e-07,
1235
+ "loss": 0.1675,
1236
+ "step": 4775
1237
+ },
1238
+ {
1239
+ "epoch": 16.47,
1240
+ "learning_rate": 4.6275e-07,
1241
+ "loss": 0.1672,
1242
+ "step": 4800
1243
+ },
1244
+ {
1245
+ "epoch": 16.55,
1246
+ "learning_rate": 4.5962499999999996e-07,
1247
+ "loss": 0.1671,
1248
+ "step": 4825
1249
+ },
1250
+ {
1251
+ "epoch": 16.64,
1252
+ "learning_rate": 4.565e-07,
1253
+ "loss": 0.1686,
1254
+ "step": 4850
1255
+ },
1256
+ {
1257
+ "epoch": 16.72,
1258
+ "learning_rate": 4.5337499999999997e-07,
1259
+ "loss": 0.1732,
1260
+ "step": 4875
1261
+ },
1262
+ {
1263
+ "epoch": 16.81,
1264
+ "learning_rate": 4.5024999999999995e-07,
1265
+ "loss": 0.1645,
1266
+ "step": 4900
1267
+ },
1268
+ {
1269
+ "epoch": 16.9,
1270
+ "learning_rate": 4.47125e-07,
1271
+ "loss": 0.1688,
1272
+ "step": 4925
1273
+ },
1274
+ {
1275
+ "epoch": 16.98,
1276
+ "learning_rate": 4.44e-07,
1277
+ "loss": 0.1627,
1278
+ "step": 4950
1279
+ },
1280
+ {
1281
+ "epoch": 17.07,
1282
+ "learning_rate": 4.40875e-07,
1283
+ "loss": 0.1642,
1284
+ "step": 4975
1285
+ },
1286
+ {
1287
+ "epoch": 17.15,
1288
+ "learning_rate": 4.3774999999999996e-07,
1289
+ "loss": 0.1629,
1290
+ "step": 5000
1291
+ },
1292
+ {
1293
+ "epoch": 17.15,
1294
+ "eval_loss": 0.2214428037405014,
1295
+ "eval_runtime": 1901.3668,
1296
+ "eval_samples_per_second": 4.899,
1297
+ "eval_steps_per_second": 0.154,
1298
+ "eval_wer": 30.81706978783567,
1299
+ "step": 5000
1300
+ },
1301
+ {
1302
+ "epoch": 17.24,
1303
+ "learning_rate": 4.34625e-07,
1304
+ "loss": 0.1681,
1305
+ "step": 5025
1306
+ },
1307
+ {
1308
+ "epoch": 17.32,
1309
+ "learning_rate": 4.3149999999999997e-07,
1310
+ "loss": 0.1691,
1311
+ "step": 5050
1312
+ },
1313
+ {
1314
+ "epoch": 17.41,
1315
+ "learning_rate": 4.28375e-07,
1316
+ "loss": 0.1663,
1317
+ "step": 5075
1318
+ },
1319
+ {
1320
+ "epoch": 17.5,
1321
+ "learning_rate": 4.2524999999999997e-07,
1322
+ "loss": 0.1643,
1323
+ "step": 5100
1324
+ },
1325
+ {
1326
+ "epoch": 17.58,
1327
+ "learning_rate": 4.2212499999999995e-07,
1328
+ "loss": 0.1619,
1329
+ "step": 5125
1330
+ },
1331
+ {
1332
+ "epoch": 17.67,
1333
+ "learning_rate": 4.19e-07,
1334
+ "loss": 0.1639,
1335
+ "step": 5150
1336
+ },
1337
+ {
1338
+ "epoch": 17.75,
1339
+ "learning_rate": 4.1587499999999996e-07,
1340
+ "loss": 0.1662,
1341
+ "step": 5175
1342
+ },
1343
+ {
1344
+ "epoch": 17.84,
1345
+ "learning_rate": 4.1275e-07,
1346
+ "loss": 0.1692,
1347
+ "step": 5200
1348
+ },
1349
+ {
1350
+ "epoch": 17.92,
1351
+ "learning_rate": 4.09625e-07,
1352
+ "loss": 0.1642,
1353
+ "step": 5225
1354
+ },
1355
+ {
1356
+ "epoch": 18.01,
1357
+ "learning_rate": 4.0649999999999994e-07,
1358
+ "loss": 0.1653,
1359
+ "step": 5250
1360
+ },
1361
+ {
1362
+ "epoch": 18.1,
1363
+ "learning_rate": 4.0337499999999997e-07,
1364
+ "loss": 0.1674,
1365
+ "step": 5275
1366
+ },
1367
+ {
1368
+ "epoch": 18.18,
1369
+ "learning_rate": 4.0025e-07,
1370
+ "loss": 0.1631,
1371
+ "step": 5300
1372
+ },
1373
+ {
1374
+ "epoch": 18.27,
1375
+ "learning_rate": 3.97125e-07,
1376
+ "loss": 0.1627,
1377
+ "step": 5325
1378
+ },
1379
+ {
1380
+ "epoch": 18.35,
1381
+ "learning_rate": 3.94e-07,
1382
+ "loss": 0.1633,
1383
+ "step": 5350
1384
+ },
1385
+ {
1386
+ "epoch": 18.44,
1387
+ "learning_rate": 3.9087499999999993e-07,
1388
+ "loss": 0.1612,
1389
+ "step": 5375
1390
+ },
1391
+ {
1392
+ "epoch": 18.52,
1393
+ "learning_rate": 3.8774999999999996e-07,
1394
+ "loss": 0.1591,
1395
+ "step": 5400
1396
+ },
1397
+ {
1398
+ "epoch": 18.61,
1399
+ "learning_rate": 3.84625e-07,
1400
+ "loss": 0.166,
1401
+ "step": 5425
1402
+ },
1403
+ {
1404
+ "epoch": 18.7,
1405
+ "learning_rate": 3.8149999999999997e-07,
1406
+ "loss": 0.1656,
1407
+ "step": 5450
1408
+ },
1409
+ {
1410
+ "epoch": 18.78,
1411
+ "learning_rate": 3.78375e-07,
1412
+ "loss": 0.1649,
1413
+ "step": 5475
1414
+ },
1415
+ {
1416
+ "epoch": 18.87,
1417
+ "learning_rate": 3.7525e-07,
1418
+ "loss": 0.1636,
1419
+ "step": 5500
1420
+ },
1421
+ {
1422
+ "epoch": 18.87,
1423
+ "eval_loss": 0.21942444145679474,
1424
+ "eval_runtime": 1897.9841,
1425
+ "eval_samples_per_second": 4.907,
1426
+ "eval_steps_per_second": 0.154,
1427
+ "eval_wer": 30.43676679820676,
1428
+ "step": 5500
1429
+ }
1430
+ ],
1431
+ "logging_steps": 25,
1432
+ "max_steps": 8500,
1433
+ "num_input_tokens_seen": 0,
1434
+ "num_train_epochs": 30,
1435
+ "save_steps": 500,
1436
+ "total_flos": 2.279802921025536e+19,
1437
+ "train_batch_size": 32,
1438
+ "trial_name": null,
1439
+ "trial_params": null
1440
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44a7ebe1b9bfc1e510636da8f67ae032cf3f99b4d9856500a24956aca7c9ce8
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff