patrickvonplaten commited on
Commit
3ba41fa
1 Parent(s): 9bbf813

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -28
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [asapp/sew-d-small-100k](https://huggingface.co/asapp/sew-d-small-100k) on the TIMIT_ASR - NA dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.7561
22
- - Wer: 0.7971
23
 
24
  ## Model description
25
 
@@ -53,34 +53,34 @@ The following hyperparameters were used during training:
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
  | 4.2068 | 0.69 | 100 | 4.0802 | 1.0 |
56
- | 2.9806 | 1.38 | 200 | 2.9792 | 1.0 |
57
  | 2.9781 | 2.07 | 300 | 2.9408 | 1.0 |
58
  | 2.9655 | 2.76 | 400 | 2.9143 | 1.0 |
59
- | 2.8953 | 3.45 | 500 | 2.8774 | 1.0 |
60
- | 2.7712 | 4.14 | 600 | 2.7769 | 0.9999 |
61
- | 2.6662 | 4.83 | 700 | 2.6425 | 0.9789 |
62
- | 2.632 | 5.52 | 800 | 2.5142 | 1.0318 |
63
- | 2.3794 | 6.21 | 900 | 2.4360 | 1.1475 |
64
- | 2.1406 | 6.9 | 1000 | 2.2932 | 0.9962 |
65
- | 2.223 | 7.59 | 1100 | 2.1590 | 0.9281 |
66
- | 2.3607 | 8.28 | 1200 | 2.0553 | 0.8682 |
67
- | 2.1058 | 8.97 | 1300 | 2.0443 | 0.8902 |
68
- | 1.8191 | 9.66 | 1400 | 1.9586 | 0.8237 |
69
- | 1.7013 | 10.34 | 1500 | 1.9586 | 0.8689 |
70
- | 2.2289 | 11.03 | 1600 | 1.9082 | 0.8611 |
71
- | 1.9125 | 11.72 | 1700 | 1.8772 | 0.8150 |
72
- | 1.6424 | 12.41 | 1800 | 1.8671 | 0.7871 |
73
- | 1.6553 | 13.1 | 1900 | 1.8192 | 0.8121 |
74
- | 2.0382 | 13.79 | 2000 | 1.8146 | 0.8440 |
75
- | 1.8785 | 14.48 | 2100 | 1.8094 | 0.8202 |
76
- | 1.6148 | 15.17 | 2200 | 1.8131 | 0.8234 |
77
- | 1.4948 | 15.86 | 2300 | 1.7969 | 0.8256 |
78
- | 1.8844 | 16.55 | 2400 | 1.7790 | 0.8067 |
79
- | 1.8099 | 17.24 | 2500 | 1.7783 | 0.8073 |
80
- | 1.5488 | 17.93 | 2600 | 1.7668 | 0.7971 |
81
- | 1.458 | 18.62 | 2700 | 1.7623 | 0.7973 |
82
- | 1.7656 | 19.31 | 2800 | 1.7574 | 0.8013 |
83
- | 1.7583 | 20.0 | 2900 | 1.7561 | 0.7971 |
84
 
85
 
86
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [asapp/sew-d-small-100k](https://huggingface.co/asapp/sew-d-small-100k) on the TIMIT_ASR - NA dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.7541
22
+ - Wer: 0.8061
23
 
24
  ## Model description
25
 
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
  | 4.2068 | 0.69 | 100 | 4.0802 | 1.0 |
56
+ | 2.9805 | 1.38 | 200 | 2.9792 | 1.0 |
57
  | 2.9781 | 2.07 | 300 | 2.9408 | 1.0 |
58
  | 2.9655 | 2.76 | 400 | 2.9143 | 1.0 |
59
+ | 2.8953 | 3.45 | 500 | 2.8775 | 1.0 |
60
+ | 2.7718 | 4.14 | 600 | 2.7787 | 1.0 |
61
+ | 2.6711 | 4.83 | 700 | 2.6401 | 0.9786 |
62
+ | 2.6403 | 5.52 | 800 | 2.5435 | 1.0392 |
63
+ | 2.4052 | 6.21 | 900 | 2.4580 | 1.0706 |
64
+ | 2.1708 | 6.9 | 1000 | 2.2800 | 1.0090 |
65
+ | 2.2555 | 7.59 | 1100 | 2.1493 | 0.9579 |
66
+ | 2.3673 | 8.28 | 1200 | 2.0709 | 0.9051 |
67
+ | 2.091 | 8.97 | 1300 | 2.0258 | 0.8926 |
68
+ | 1.8433 | 9.66 | 1400 | 1.9645 | 0.8243 |
69
+ | 1.6824 | 10.34 | 1500 | 1.9211 | 0.8707 |
70
+ | 2.2282 | 11.03 | 1600 | 1.8914 | 0.8695 |
71
+ | 1.9027 | 11.72 | 1700 | 1.8718 | 0.8343 |
72
+ | 1.6303 | 12.41 | 1800 | 1.8646 | 0.8232 |
73
+ | 1.648 | 13.1 | 1900 | 1.8297 | 0.8177 |
74
+ | 2.0429 | 13.79 | 2000 | 1.8127 | 0.8642 |
75
+ | 1.8833 | 14.48 | 2100 | 1.8005 | 0.8307 |
76
+ | 1.5996 | 15.17 | 2200 | 1.7926 | 0.8467 |
77
+ | 1.4876 | 15.86 | 2300 | 1.7795 | 0.8341 |
78
+ | 1.8925 | 16.55 | 2400 | 1.7716 | 0.8199 |
79
+ | 1.814 | 17.24 | 2500 | 1.7846 | 0.8086 |
80
+ | 1.536 | 17.93 | 2600 | 1.7655 | 0.8019 |
81
+ | 1.4476 | 18.62 | 2700 | 1.7599 | 0.8070 |
82
+ | 1.7629 | 19.31 | 2800 | 1.7589 | 0.8119 |
83
+ | 1.7646 | 20.0 | 2900 | 1.7541 | 0.8061 |
84
 
85
 
86
  ### Framework versions