Hugging Face's logo

ones
/
wav2vec2-base-timit-demo-google-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files Metrics Community
1
ones commited on
Commit
7103a7a
·
1 Parent(s): 35a5767

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -31
README.md CHANGED
@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.5237
18
- - Wer: 0.3346
19
 
20
  ## Model description
21
 
@@ -48,35 +48,35 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Wer |
50
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
- | 3.5358 | 1.0 | 500 | 1.5944 | 1.0201 |
52
- | 0.8368 | 2.01 | 1000 | 0.5641 | 0.5463 |
53
- | 0.4255 | 3.01 | 1500 | 0.4739 | 0.4685 |
54
- | 0.304 | 4.02 | 2000 | 0.4171 | 0.4308 |
55
- | 0.2395 | 5.02 | 2500 | 0.4240 | 0.4073 |
56
- | 0.1912 | 6.02 | 3000 | 0.4893 | 0.4047 |
57
- | 0.1645 | 7.03 | 3500 | 0.4746 | 0.3889 |
58
- | 0.1435 | 8.03 | 4000 | 0.4155 | 0.3854 |
59
- | 0.124 | 9.04 | 4500 | 0.4588 | 0.3723 |
60
- | 0.1088 | 10.04 | 5000 | 0.4506 | 0.3741 |
61
- | 0.1016 | 11.04 | 5500 | 0.4440 | 0.3697 |
62
- | 0.085 | 12.05 | 6000 | 0.4652 | 0.3705 |
63
- | 0.0814 | 13.05 | 6500 | 0.5103 | 0.3631 |
64
- | 0.075 | 14.06 | 7000 | 0.4837 | 0.3626 |
65
- | 0.069 | 15.06 | 7500 | 0.4987 | 0.3614 |
66
- | 0.058 | 16.06 | 8000 | 0.4940 | 0.3554 |
67
- | 0.0556 | 17.07 | 8500 | 0.5129 | 0.3582 |
68
- | 0.0528 | 18.07 | 9000 | 0.5216 | 0.3616 |
69
- | 0.0458 | 19.08 | 9500 | 0.5110 | 0.3521 |
70
- | 0.0446 | 20.08 | 10000 | 0.5013 | 0.3539 |
71
- | 0.0411 | 21.08 | 10500 | 0.5126 | 0.3457 |
72
- | 0.0361 | 22.09 | 11000 | 0.5372 | 0.3403 |
73
- | 0.0326 | 23.09 | 11500 | 0.5216 | 0.3427 |
74
- | 0.0313 | 24.1 | 12000 | 0.5583 | 0.3426 |
75
- | 0.0281 | 25.1 | 12500 | 0.5330 | 0.3422 |
76
- | 0.0239 | 26.1 | 13000 | 0.5325 | 0.3377 |
77
- | 0.0246 | 27.11 | 13500 | 0.5414 | 0.3369 |
78
- | 0.0229 | 28.11 | 14000 | 0.5176 | 0.3345 |
79
- | 0.0227 | 29.12 | 14500 | 0.5237 | 0.3346 |
80
 
81
 
82
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.5112
18
+ - Wer: 0.9988
19
 
20
  ## Model description
21
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Wer |
50
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
+ | 3.5557 | 1.0 | 500 | 1.6786 | 1.0 |
52
+ | 0.8407 | 2.01 | 1000 | 0.5356 | 0.9988 |
53
+ | 0.4297 | 3.01 | 1500 | 0.4431 | 0.9988 |
54
+ | 0.2989 | 4.02 | 2000 | 0.4191 | 0.9988 |
55
+ | 0.2338 | 5.02 | 2500 | 0.4251 | 0.9988 |
56
+ | 0.1993 | 6.02 | 3000 | 0.4618 | 0.9988 |
57
+ | 0.1585 | 7.03 | 3500 | 0.4577 | 0.9988 |
58
+ | 0.1386 | 8.03 | 4000 | 0.4099 | 0.9982 |
59
+ | 0.1234 | 9.04 | 4500 | 0.4945 | 0.9988 |
60
+ | 0.1162 | 10.04 | 5000 | 0.4597 | 0.9988 |
61
+ | 0.1008 | 11.04 | 5500 | 0.4563 | 0.9988 |
62
+ | 0.0894 | 12.05 | 6000 | 0.5157 | 0.9988 |
63
+ | 0.083 | 13.05 | 6500 | 0.5027 | 0.9988 |
64
+ | 0.0735 | 14.06 | 7000 | 0.4905 | 0.9994 |
65
+ | 0.0686 | 15.06 | 7500 | 0.4552 | 0.9988 |
66
+ | 0.0632 | 16.06 | 8000 | 0.5522 | 0.9988 |
67
+ | 0.061 | 17.07 | 8500 | 0.4874 | 0.9988 |
68
+ | 0.0626 | 18.07 | 9000 | 0.5243 | 0.9988 |
69
+ | 0.0475 | 19.08 | 9500 | 0.4798 | 0.9988 |
70
+ | 0.0447 | 20.08 | 10000 | 0.5250 | 0.9988 |
71
+ | 0.0432 | 21.08 | 10500 | 0.5195 | 0.9988 |
72
+ | 0.0358 | 22.09 | 11000 | 0.5008 | 0.9988 |
73
+ | 0.0319 | 23.09 | 11500 | 0.5376 | 0.9988 |
74
+ | 0.0334 | 24.1 | 12000 | 0.5149 | 0.9988 |
75
+ | 0.0269 | 25.1 | 12500 | 0.4911 | 0.9988 |
76
+ | 0.0275 | 26.1 | 13000 | 0.4907 | 0.9988 |
77
+ | 0.027 | 27.11 | 13500 | 0.4992 | 0.9988 |
78
+ | 0.0239 | 28.11 | 14000 | 0.5021 | 0.9988 |
79
+ | 0.0233 | 29.12 | 14500 | 0.5112 | 0.9988 |
80
 
81
 
82
  ### Framework versions