Hugging Face's logo

yip-i
/
wav2vec2-demo-M01-2

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
1
yip-i commited on
Commit
18ba3ac
·
1 Parent(s): 47106a5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -35
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-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.9048
18
- - Wer: 0.9767
19
 
20
  ## Model description
21
 
@@ -47,39 +47,39 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Wer |
49
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
50
- | 22.8713 | 0.9 | 500 | 3.3195 | 1.0 |
51
- | 3.3669 | 1.8 | 1000 | 3.0433 | 1.0 |
52
- | 2.8846 | 2.7 | 1500 | 2.7503 | 1.0 |
53
- | 2.5161 | 3.6 | 2000 | 2.2072 | 1.1986 |
54
- | 1.5627 | 4.5 | 2500 | 1.5431 | 1.3703 |
55
- | 1.0728 | 5.41 | 3000 | 1.3884 | 1.3435 |
56
- | 0.8312 | 6.31 | 3500 | 1.2063 | 1.1979 |
57
- | 0.7131 | 7.21 | 4000 | 1.2167 | 1.1922 |
58
- | 0.5736 | 8.11 | 4500 | 1.1290 | 1.1117 |
59
- | 0.5117 | 9.01 | 5000 | 1.3774 | 1.1364 |
60
- | 0.447 | 9.91 | 5500 | 1.3066 | 1.0763 |
61
- | 0.4139 | 10.81 | 6000 | 1.2730 | 1.0869 |
62
- | 0.366 | 11.71 | 6500 | 1.5916 | 1.0820 |
63
- | 0.3435 | 12.61 | 7000 | 1.3768 | 1.0615 |
64
- | 0.3266 | 13.51 | 7500 | 1.3549 | 1.0113 |
65
- | 0.3066 | 14.41 | 8000 | 1.4171 | 0.9929 |
66
- | 0.2756 | 15.32 | 8500 | 1.3902 | 0.9809 |
67
- | 0.26 | 16.22 | 9000 | 1.7141 | 1.0177 |
68
- | 0.2523 | 17.12 | 9500 | 1.4916 | 0.9788 |
69
- | 0.235 | 18.02 | 10000 | 1.5042 | 0.9887 |
70
- | 0.222 | 18.92 | 10500 | 1.5941 | 1.0021 |
71
- | 0.2108 | 19.82 | 11000 | 1.7729 | 1.0028 |
72
- | 0.1997 | 20.72 | 11500 | 1.8158 | 1.0035 |
73
- | 0.1625 | 21.62 | 12000 | 1.6591 | 0.9788 |
74
- | 0.1802 | 22.52 | 12500 | 1.7722 | 0.9894 |
75
- | 0.1535 | 23.42 | 13000 | 1.9380 | 0.9830 |
76
- | 0.1562 | 24.32 | 13500 | 1.7546 | 0.9816 |
77
- | 0.1411 | 25.23 | 14000 | 1.8759 | 0.9908 |
78
- | 0.1271 | 26.13 | 14500 | 1.9553 | 0.9915 |
79
- | 0.1365 | 27.03 | 15000 | 1.9331 | 0.9668 |
80
- | 0.1353 | 27.93 | 15500 | 1.9489 | 0.9873 |
81
- | 0.129 | 28.83 | 16000 | 1.8907 | 0.9816 |
82
- | 0.1248 | 29.73 | 16500 | 1.9048 | 0.9767 |
83
 
84
 
85
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.8002
18
+ - Wer: 0.9717
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Wer |
49
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
50
+ | 23.0778 | 0.9 | 500 | 3.3183 | 1.0 |
51
+ | 3.3341 | 1.8 | 1000 | 3.1046 | 1.0 |
52
+ | 2.8465 | 2.7 | 1500 | 2.7012 | 1.0 |
53
+ | 2.4301 | 3.6 | 2000 | 1.9785 | 1.3025 |
54
+ | 1.5285 | 4.5 | 2500 | 1.5775 | 1.4170 |
55
+ | 1.055 | 5.41 | 3000 | 1.5070 | 1.3753 |
56
+ | 0.8075 | 6.31 | 3500 | 1.3811 | 1.2509 |
57
+ | 0.6867 | 7.21 | 4000 | 1.2362 | 1.2007 |
58
+ | 0.566 | 8.11 | 4500 | 1.6537 | 1.2064 |
59
+ | 0.4967 | 9.01 | 5000 | 1.5271 | 1.1562 |
60
+ | 0.4337 | 9.91 | 5500 | 1.2359 | 1.1046 |
61
+ | 0.3941 | 10.81 | 6000 | 1.5255 | 1.1237 |
62
+ | 0.3612 | 11.71 | 6500 | 1.3686 | 1.0890 |
63
+ | 0.3237 | 12.61 | 7000 | 1.1992 | 1.0629 |
64
+ | 0.3085 | 13.51 | 7500 | 1.5883 | 1.0834 |
65
+ | 0.3003 | 14.41 | 8000 | 1.7352 | 1.0686 |
66
+ | 0.2859 | 15.32 | 8500 | 1.4790 | 0.9958 |
67
+ | 0.2495 | 16.22 | 9000 | 1.6757 | 1.0155 |
68
+ | 0.2329 | 17.12 | 9500 | 1.5789 | 1.0283 |
69
+ | 0.2241 | 18.02 | 10000 | 1.5147 | 0.9922 |
70
+ | 0.215 | 18.92 | 10500 | 1.4684 | 0.9965 |
71
+ | 0.202 | 19.82 | 11000 | 1.5099 | 0.9760 |
72
+ | 0.1942 | 20.72 | 11500 | 1.8195 | 0.9837 |
73
+ | 0.1627 | 21.62 | 12000 | 1.8089 | 1.0021 |
74
+ | 0.1782 | 22.52 | 12500 | 1.6944 | 0.9710 |
75
+ | 0.1566 | 23.42 | 13000 | 1.5881 | 0.9682 |
76
+ | 0.1471 | 24.32 | 13500 | 1.6741 | 0.9654 |
77
+ | 0.1355 | 25.23 | 14000 | 1.6183 | 0.9576 |
78
+ | 0.1253 | 26.13 | 14500 | 1.5730 | 0.9696 |
79
+ | 0.1245 | 27.03 | 15000 | 1.6876 | 0.9689 |
80
+ | 0.1258 | 27.93 | 15500 | 1.7535 | 0.9802 |
81
+ | 0.1217 | 28.83 | 16000 | 1.7710 | 0.9661 |
82
+ | 0.1074 | 29.73 | 16500 | 1.8002 | 0.9717 |
83
 
84
 
85
  ### Framework versions