pedroferreira commited on
Commit
dc22010
1 Parent(s): 12dabaa

End of training

Browse files
Files changed (5) hide show
  1. README.md +75 -0
  2. config.json +1 -1
  3. generation_config.json +227 -0
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-tiny
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - PolyAI/minds14
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: whisper-tiny-minds14-US-finetuned
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: PolyAI/minds14
18
+ type: PolyAI/minds14
19
+ metrics:
20
+ - name: Wer
21
+ type: wer
22
+ value: 0.2687576875768758
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # whisper-tiny-minds14-US-finetuned
29
+
30
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.2827
33
+ - Wer Ortho: 26.6409
34
+ - Wer: 0.2688
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 1e-05
54
+ - train_batch_size: 16
55
+ - eval_batch_size: 16
56
+ - seed: 42
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: cosine
59
+ - lr_scheduler_warmup_steps: 50
60
+ - training_steps: 500
61
+ - mixed_precision_training: Native AMP
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
66
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
67
+ | 0.0014 | 17.24 | 500 | 0.2827 | 26.6409 | 0.2688 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.36.2
73
+ - Pytorch 2.1.2+cu121
74
+ - Datasets 2.16.0
75
+ - Tokenizers 0.15.0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-tiny",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
1
  {
2
+ "_name_or_path": "weiren119/whisper-tiny-finetuned-PolyAI-minds14",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
generation_config.json ADDED
@@ -0,0 +1,227 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "begin_suppress_tokens": [
3
+ 220,
4
+ 50257
5
+ ],
6
+ "bos_token_id": 50257,
7
+ "decoder_start_token_id": 50258,
8
+ "eos_token_id": 50257,
9
+ "forced_decoder_ids": [
10
+ [
11
+ 1,
12
+ 50259
13
+ ],
14
+ [
15
+ 2,
16
+ 50359
17
+ ],
18
+ [
19
+ 3,
20
+ 50363
21
+ ]
22
+ ],
23
+ "is_multilingual": true,
24
+ "lang_to_id": {
25
+ "<|af|>": 50327,
26
+ "<|am|>": 50334,
27
+ "<|ar|>": 50272,
28
+ "<|as|>": 50350,
29
+ "<|az|>": 50304,
30
+ "<|ba|>": 50355,
31
+ "<|be|>": 50330,
32
+ "<|bg|>": 50292,
33
+ "<|bn|>": 50302,
34
+ "<|bo|>": 50347,
35
+ "<|br|>": 50309,
36
+ "<|bs|>": 50315,
37
+ "<|ca|>": 50270,
38
+ "<|cs|>": 50283,
39
+ "<|cy|>": 50297,
40
+ "<|da|>": 50285,
41
+ "<|de|>": 50261,
42
+ "<|el|>": 50281,
43
+ "<|en|>": 50259,
44
+ "<|es|>": 50262,
45
+ "<|et|>": 50307,
46
+ "<|eu|>": 50310,
47
+ "<|fa|>": 50300,
48
+ "<|fi|>": 50277,
49
+ "<|fo|>": 50338,
50
+ "<|fr|>": 50265,
51
+ "<|gl|>": 50319,
52
+ "<|gu|>": 50333,
53
+ "<|haw|>": 50352,
54
+ "<|ha|>": 50354,
55
+ "<|he|>": 50279,
56
+ "<|hi|>": 50276,
57
+ "<|hr|>": 50291,
58
+ "<|ht|>": 50339,
59
+ "<|hu|>": 50286,
60
+ "<|hy|>": 50312,
61
+ "<|id|>": 50275,
62
+ "<|is|>": 50311,
63
+ "<|it|>": 50274,
64
+ "<|ja|>": 50266,
65
+ "<|jw|>": 50356,
66
+ "<|ka|>": 50329,
67
+ "<|kk|>": 50316,
68
+ "<|km|>": 50323,
69
+ "<|kn|>": 50306,
70
+ "<|ko|>": 50264,
71
+ "<|la|>": 50294,
72
+ "<|lb|>": 50345,
73
+ "<|ln|>": 50353,
74
+ "<|lo|>": 50336,
75
+ "<|lt|>": 50293,
76
+ "<|lv|>": 50301,
77
+ "<|mg|>": 50349,
78
+ "<|mi|>": 50295,
79
+ "<|mk|>": 50308,
80
+ "<|ml|>": 50296,
81
+ "<|mn|>": 50314,
82
+ "<|mr|>": 50320,
83
+ "<|ms|>": 50282,
84
+ "<|mt|>": 50343,
85
+ "<|my|>": 50346,
86
+ "<|ne|>": 50313,
87
+ "<|nl|>": 50271,
88
+ "<|nn|>": 50342,
89
+ "<|no|>": 50288,
90
+ "<|oc|>": 50328,
91
+ "<|pa|>": 50321,
92
+ "<|pl|>": 50269,
93
+ "<|ps|>": 50340,
94
+ "<|pt|>": 50267,
95
+ "<|ro|>": 50284,
96
+ "<|ru|>": 50263,
97
+ "<|sa|>": 50344,
98
+ "<|sd|>": 50332,
99
+ "<|si|>": 50322,
100
+ "<|sk|>": 50298,
101
+ "<|sl|>": 50305,
102
+ "<|sn|>": 50324,
103
+ "<|so|>": 50326,
104
+ "<|sq|>": 50317,
105
+ "<|sr|>": 50303,
106
+ "<|su|>": 50357,
107
+ "<|sv|>": 50273,
108
+ "<|sw|>": 50318,
109
+ "<|ta|>": 50287,
110
+ "<|te|>": 50299,
111
+ "<|tg|>": 50331,
112
+ "<|th|>": 50289,
113
+ "<|tk|>": 50341,
114
+ "<|tl|>": 50348,
115
+ "<|tr|>": 50268,
116
+ "<|tt|>": 50351,
117
+ "<|uk|>": 50280,
118
+ "<|ur|>": 50290,
119
+ "<|uz|>": 50337,
120
+ "<|vi|>": 50278,
121
+ "<|yi|>": 50335,
122
+ "<|yo|>": 50325,
123
+ "<|zh|>": 50260
124
+ },
125
+ "language": "english",
126
+ "max_initial_timestamp_index": 1,
127
+ "max_length": 448,
128
+ "no_timestamps_token_id": 50363,
129
+ "pad_token_id": 50257,
130
+ "return_timestamps": false,
131
+ "suppress_tokens": [
132
+ 1,
133
+ 2,
134
+ 7,
135
+ 8,
136
+ 9,
137
+ 10,
138
+ 14,
139
+ 25,
140
+ 26,
141
+ 27,
142
+ 28,
143
+ 29,
144
+ 31,
145
+ 58,
146
+ 59,
147
+ 60,
148
+ 61,
149
+ 62,
150
+ 63,
151
+ 90,
152
+ 91,
153
+ 92,
154
+ 93,
155
+ 359,
156
+ 503,
157
+ 522,
158
+ 542,
159
+ 873,
160
+ 893,
161
+ 902,
162
+ 918,
163
+ 922,
164
+ 931,
165
+ 1350,
166
+ 1853,
167
+ 1982,
168
+ 2460,
169
+ 2627,
170
+ 3246,
171
+ 3253,
172
+ 3268,
173
+ 3536,
174
+ 3846,
175
+ 3961,
176
+ 4183,
177
+ 4667,
178
+ 6585,
179
+ 6647,
180
+ 7273,
181
+ 9061,
182
+ 9383,
183
+ 10428,
184
+ 10929,
185
+ 11938,
186
+ 12033,
187
+ 12331,
188
+ 12562,
189
+ 13793,
190
+ 14157,
191
+ 14635,
192
+ 15265,
193
+ 15618,
194
+ 16553,
195
+ 16604,
196
+ 18362,
197
+ 18956,
198
+ 20075,
199
+ 21675,
200
+ 22520,
201
+ 26130,
202
+ 26161,
203
+ 26435,
204
+ 28279,
205
+ 29464,
206
+ 31650,
207
+ 32302,
208
+ 32470,
209
+ 36865,
210
+ 42863,
211
+ 47425,
212
+ 49870,
213
+ 50254,
214
+ 50258,
215
+ 50358,
216
+ 50359,
217
+ 50360,
218
+ 50361,
219
+ 50362
220
+ ],
221
+ "task": "transcribe",
222
+ "task_to_id": {
223
+ "transcribe": 50359,
224
+ "translate": 50358
225
+ },
226
+ "transformers_version": "4.36.2"
227
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b670b93dc274f6ffce4897f029809522b42341aa1c001290df595558b4436ebc
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb116849ecd07743744c5309a692ad65afce8cb358609bf4fa7d51f9a333a2b
3
  size 151061672
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a12b0a1071d0e9591eb8ab1e49df2094c5822fdf63800633f98a496063a3ad60
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03582704a8e36b2f25d8e9b81c477dcbead0fb64f9e3530bb0dddd35aa431383
3
  size 4856