Hugging Face's logo

greenw0lf
/
wav2vec2-large-xls-r-1b-frisian-cv-8-large-train

Automatic Speech Recognition
Transformers
PyTorch
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
greenw0lf commited on
Commit
f670364
•
1 Parent(s): 6a4c832

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +157 -0
README.md ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_8_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: wav2vec2-large-xls-r-1b-frisian-cv-8-large-train
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_8_0
17
+ type: common_voice_8_0
18
+ config: fy-NL
19
+ split: validation
20
+ args: fy-NL
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.04206541922582488
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # wav2vec2-large-xls-r-1b-frisian-cv-8-large-train
31
+
32
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice_8_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0444
35
+ - Wer: 0.0421
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 3e-05
55
+ - train_batch_size: 36
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 40
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
68
+ | 7.2522 | 0.48 | 400 | 3.1028 | 1.0 |
69
+ | 3.0052 | 0.97 | 800 | 2.9334 | 1.0 |
70
+ | 2.0865 | 1.45 | 1200 | 0.7288 | 0.6646 |
71
+ | 1.1654 | 1.93 | 1600 | 0.4298 | 0.4196 |
72
+ | 0.9665 | 2.41 | 2000 | 0.3134 | 0.3162 |
73
+ | 0.7891 | 2.9 | 2400 | 0.2378 | 0.2587 |
74
+ | 0.8366 | 3.38 | 2800 | 0.1896 | 0.2016 |
75
+ | 0.8606 | 3.86 | 3200 | 0.1647 | 0.1903 |
76
+ | 0.7536 | 4.34 | 3600 | 0.1486 | 0.1573 |
77
+ | 0.632 | 4.83 | 4000 | 0.1341 | 0.1450 |
78
+ | 0.5198 | 5.31 | 4400 | 0.1223 | 0.1415 |
79
+ | 0.4998 | 5.79 | 4800 | 0.1155 | 0.1388 |
80
+ | 0.4273 | 6.27 | 5200 | 0.1132 | 0.1302 |
81
+ | 0.3982 | 6.76 | 5600 | 0.1036 | 0.1102 |
82
+ | 0.3964 | 7.24 | 6000 | 0.0988 | 0.1209 |
83
+ | 0.3848 | 7.72 | 6400 | 0.0995 | 0.0985 |
84
+ | 0.3702 | 8.2 | 6800 | 0.0969 | 0.0945 |
85
+ | 0.3612 | 8.69 | 7200 | 0.0899 | 0.0967 |
86
+ | 0.3518 | 9.17 | 7600 | 0.0856 | 0.1061 |
87
+ | 0.3371 | 9.65 | 8000 | 0.0902 | 0.0875 |
88
+ | 0.3295 | 10.13 | 8400 | 0.0819 | 0.0914 |
89
+ | 0.3157 | 10.62 | 8800 | 0.0785 | 0.0937 |
90
+ | 0.3025 | 11.1 | 9200 | 0.0782 | 0.0804 |
91
+ | 0.3092 | 11.58 | 9600 | 0.0758 | 0.0845 |
92
+ | 0.301 | 12.06 | 10000 | 0.0775 | 0.0847 |
93
+ | 0.3016 | 12.55 | 10400 | 0.0730 | 0.0776 |
94
+ | 0.2892 | 13.03 | 10800 | 0.0719 | 0.0735 |
95
+ | 0.283 | 13.51 | 11200 | 0.0728 | 0.0727 |
96
+ | 0.2806 | 13.99 | 11600 | 0.0694 | 0.0710 |
97
+ | 0.2639 | 14.48 | 12000 | 0.0705 | 0.0703 |
98
+ | 0.2606 | 14.96 | 12400 | 0.0652 | 0.0668 |
99
+ | 0.2595 | 15.44 | 12800 | 0.0638 | 0.0691 |
100
+ | 0.2611 | 15.92 | 13200 | 0.0636 | 0.0713 |
101
+ | 0.246 | 16.41 | 13600 | 0.0632 | 0.0653 |
102
+ | 0.2544 | 16.89 | 14000 | 0.0605 | 0.0638 |
103
+ | 0.2509 | 17.37 | 14400 | 0.0640 | 0.0646 |
104
+ | 0.2381 | 17.85 | 14800 | 0.0604 | 0.0663 |
105
+ | 0.2336 | 18.34 | 15200 | 0.0590 | 0.0628 |
106
+ | 0.2285 | 18.82 | 15600 | 0.0580 | 0.0612 |
107
+ | 0.2362 | 19.3 | 16000 | 0.0655 | 0.0638 |
108
+ | 0.2279 | 19.78 | 16400 | 0.0611 | 0.0669 |
109
+ | 0.2228 | 20.27 | 16800 | 0.0606 | 0.0621 |
110
+ | 0.2242 | 20.75 | 17200 | 0.0560 | 0.0575 |
111
+ | 0.2053 | 21.23 | 17600 | 0.0571 | 0.0572 |
112
+ | 0.2097 | 21.71 | 18000 | 0.0557 | 0.0555 |
113
+ | 0.2072 | 22.2 | 18400 | 0.0563 | 0.0576 |
114
+ | 0.2076 | 22.68 | 18800 | 0.0532 | 0.0562 |
115
+ | 0.2026 | 23.16 | 19200 | 0.0531 | 0.0540 |
116
+ | 0.1941 | 23.64 | 19600 | 0.0535 | 0.0534 |
117
+ | 0.1983 | 24.13 | 20000 | 0.0528 | 0.0541 |
118
+ | 0.2075 | 24.61 | 20400 | 0.0536 | 0.0538 |
119
+ | 0.1937 | 25.09 | 20800 | 0.0532 | 0.0569 |
120
+ | 0.1943 | 25.57 | 21200 | 0.0511 | 0.0507 |
121
+ | 0.1844 | 26.06 | 21600 | 0.0521 | 0.0521 |
122
+ | 0.181 | 26.54 | 22000 | 0.0506 | 0.0507 |
123
+ | 0.1877 | 27.02 | 22400 | 0.0529 | 0.0510 |
124
+ | 0.1825 | 27.5 | 22800 | 0.0527 | 0.0498 |
125
+ | 0.1872 | 27.99 | 23200 | 0.0506 | 0.0485 |
126
+ | 0.1857 | 28.47 | 23600 | 0.0497 | 0.0492 |
127
+ | 0.1766 | 28.95 | 24000 | 0.0504 | 0.0488 |
128
+ | 0.1756 | 29.43 | 24400 | 0.0496 | 0.0482 |
129
+ | 0.1701 | 29.92 | 24800 | 0.0479 | 0.0479 |
130
+ | 0.1717 | 30.4 | 25200 | 0.0499 | 0.0468 |
131
+ | 0.1624 | 30.88 | 25600 | 0.0492 | 0.0466 |
132
+ | 0.1671 | 31.36 | 26000 | 0.0490 | 0.0461 |
133
+ | 0.1704 | 31.85 | 26400 | 0.0482 | 0.0452 |
134
+ | 0.1653 | 32.33 | 26800 | 0.0467 | 0.0446 |
135
+ | 0.158 | 32.81 | 27200 | 0.0465 | 0.0449 |
136
+ | 0.1599 | 33.29 | 27600 | 0.0473 | 0.0445 |
137
+ | 0.1558 | 33.78 | 28000 | 0.0475 | 0.0453 |
138
+ | 0.1556 | 34.26 | 28400 | 0.0462 | 0.0445 |
139
+ | 0.1591 | 34.74 | 28800 | 0.0464 | 0.0431 |
140
+ | 0.1544 | 35.22 | 29200 | 0.0476 | 0.0433 |
141
+ | 0.1576 | 35.71 | 29600 | 0.0466 | 0.0434 |
142
+ | 0.1507 | 36.19 | 30000 | 0.0451 | 0.0435 |
143
+ | 0.1501 | 36.67 | 30400 | 0.0453 | 0.0429 |
144
+ | 0.1482 | 37.15 | 30800 | 0.0439 | 0.0432 |
145
+ | 0.1518 | 37.64 | 31200 | 0.0446 | 0.0424 |
146
+ | 0.1454 | 38.12 | 31600 | 0.0449 | 0.0417 |
147
+ | 0.145 | 38.6 | 32000 | 0.0440 | 0.0421 |
148
+ | 0.147 | 39.08 | 32400 | 0.0441 | 0.0424 |
149
+ | 0.141 | 39.57 | 32800 | 0.0444 | 0.0421 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - Transformers 4.28.1
155
+ - Pytorch 2.0.0+cu117
156
+ - Datasets 2.11.0
157
+ - Tokenizers 0.13.3