Hugging Face's logo

Siyong
/
MT

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
Siyong commited on
Commit
74c738e
·
1 Parent(s): f1f4045

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -29
README.md CHANGED
@@ -14,8 +14,9 @@ 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: 1.1736
18
- - Wer: 0.6360
 
19
 
20
  ## Model description
21
 
@@ -46,33 +47,33 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Wer |
50
- |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
- | 3.0219 | 2.36 | 2000 | 2.4563 | 1.0141 |
52
- | 0.7358 | 4.73 | 4000 | 2.1121 | 0.8905 |
53
- | 0.5107 | 7.09 | 6000 | 2.0443 | 0.8587 |
54
- | 0.4013 | 9.46 | 8000 | 1.9790 | 0.8799 |
55
- | 0.3409 | 11.82 | 10000 | 1.9401 | 0.8216 |
56
- | 0.2997 | 14.18 | 12000 | 1.7686 | 0.8375 |
57
- | 0.2596 | 16.55 | 14000 | 1.6557 | 0.8604 |
58
- | 0.2352 | 18.91 | 16000 | 1.5478 | 0.7562 |
59
- | 0.2132 | 21.28 | 18000 | 1.6100 | 0.7385 |
60
- | 0.1967 | 23.64 | 20000 | 1.3982 | 0.7650 |
61
- | 0.1854 | 26.0 | 22000 | 1.3530 | 0.6837 |
62
- | 0.1675 | 28.37 | 24000 | 1.3607 | 0.7120 |
63
- | 0.1544 | 30.73 | 26000 | 1.1866 | 0.6979 |
64
- | 0.1495 | 33.1 | 28000 | 1.2665 | 0.6943 |
65
- | 0.1323 | 35.46 | 30000 | 1.4958 | 0.6820 |
66
- | 0.1247 | 37.83 | 32000 | 1.2287 | 0.6431 |
67
- | 0.1156 | 40.19 | 34000 | 1.3678 | 0.6749 |
68
- | 0.1069 | 42.55 | 36000 | 1.2598 | 0.6396 |
69
- | 0.1026 | 44.92 | 38000 | 1.1801 | 0.6979 |
70
- | 0.0928 | 47.28 | 40000 | 1.2173 | 0.6378 |
71
- | 0.0877 | 49.65 | 42000 | 1.2012 | 0.6572 |
72
- | 0.0812 | 52.01 | 44000 | 1.0857 | 0.6237 |
73
- | 0.0752 | 54.37 | 46000 | 1.2142 | 0.6254 |
74
- | 0.0695 | 56.74 | 48000 | 1.1816 | 0.6343 |
75
- | 0.064 | 59.1 | 50000 | 1.1736 | 0.6360 |
76
 
77
 
78
  ### 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: 1.3772
18
+ - Wer: 0.6859
19
+ - Cer: 0.3217
20
 
21
  ## Model description
22
 
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
52
+ | No log | 2.36 | 2000 | 2.6233 | 1.0130 | 0.6241 |
53
+ | No log | 4.73 | 4000 | 2.2206 | 0.9535 | 0.5032 |
54
+ | No log | 7.09 | 6000 | 2.3036 | 0.9368 | 0.5063 |
55
+ | 1.235 | 9.46 | 8000 | 1.9932 | 0.9275 | 0.5032 |
56
+ | 1.235 | 11.82 | 10000 | 2.0207 | 0.8922 | 0.4498 |
57
+ | 1.235 | 14.18 | 12000 | 1.6171 | 0.7993 | 0.3976 |
58
+ | 1.235 | 16.55 | 14000 | 1.6729 | 0.8309 | 0.4209 |
59
+ | 0.2779 | 18.91 | 16000 | 1.7043 | 0.8141 | 0.4340 |
60
+ | 0.2779 | 21.28 | 18000 | 1.7426 | 0.7658 | 0.3960 |
61
+ | 0.2779 | 23.64 | 20000 | 1.5230 | 0.7361 | 0.3830 |
62
+ | 0.2779 | 26.0 | 22000 | 1.4286 | 0.7658 | 0.3794 |
63
+ | 0.1929 | 28.37 | 24000 | 1.4450 | 0.7379 | 0.3644 |
64
+ | 0.1929 | 30.73 | 26000 | 1.5922 | 0.7491 | 0.3826 |
65
+ | 0.1929 | 33.1 | 28000 | 1.4443 | 0.7454 | 0.3617 |
66
+ | 0.1929 | 35.46 | 30000 | 1.5450 | 0.7268 | 0.3621 |
67
+ | 0.1394 | 37.83 | 32000 | 1.9268 | 0.7491 | 0.3763 |
68
+ | 0.1394 | 40.19 | 34000 | 1.7094 | 0.7342 | 0.3783 |
69
+ | 0.1394 | 42.55 | 36000 | 1.4024 | 0.7082 | 0.3494 |
70
+ | 0.1394 | 44.92 | 38000 | 1.4467 | 0.6840 | 0.3395 |
71
+ | 0.104 | 47.28 | 40000 | 1.4145 | 0.6933 | 0.3407 |
72
+ | 0.104 | 49.65 | 42000 | 1.3901 | 0.6970 | 0.3403 |
73
+ | 0.104 | 52.01 | 44000 | 1.3589 | 0.6636 | 0.3348 |
74
+ | 0.104 | 54.37 | 46000 | 1.3716 | 0.6952 | 0.3340 |
75
+ | 0.0781 | 56.74 | 48000 | 1.4025 | 0.6896 | 0.3312 |
76
+ | 0.0781 | 59.1 | 50000 | 1.3772 | 0.6859 | 0.3217 |
77
 
78
 
79
  ### Framework versions