toshiouchiyama commited on
Commit
595f8a0
1 Parent(s): 6ccbfa6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -7
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 [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.9506
22
- - Wer: 1254.9296
23
 
24
  ## Model description
25
 
@@ -45,14 +45,32 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 5
48
- - training_steps: 20
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-----:|:----:|:---------------:|:---------:|
54
- | No log | 1.43 | 10 | 1.2365 | 21.1268 |
55
- | No log | 2.86 | 20 | 0.9506 | 1254.9296 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3967
22
+ - Wer: 18.3755
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 5
48
+ - training_steps: 200
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | No log | 0.3 | 10 | 1.1627 | 26.0985 |
55
+ | No log | 0.61 | 20 | 0.7416 | 900.3995 |
56
+ | 1.2431 | 0.91 | 30 | 0.6344 | 60.3196 |
57
+ | 1.2431 | 1.21 | 40 | 0.5944 | 20.2397 |
58
+ | 0.5462 | 1.52 | 50 | 0.5341 | 19.3076 |
59
+ | 0.5462 | 1.82 | 60 | 0.4953 | 18.5087 |
60
+ | 0.5462 | 2.12 | 70 | 0.4715 | 19.9734 |
61
+ | 0.3259 | 2.42 | 80 | 0.4469 | 18.2423 |
62
+ | 0.3259 | 2.73 | 90 | 0.4246 | 19.7071 |
63
+ | 0.1986 | 3.03 | 100 | 0.4076 | 19.0413 |
64
+ | 0.1986 | 3.33 | 110 | 0.3949 | 17.7097 |
65
+ | 0.1986 | 3.64 | 120 | 0.4008 | 20.5060 |
66
+ | 0.1101 | 3.94 | 130 | 0.3892 | 18.3755 |
67
+ | 0.1101 | 4.24 | 140 | 0.3873 | 18.3755 |
68
+ | 0.0695 | 4.55 | 150 | 0.3930 | 19.7071 |
69
+ | 0.0695 | 4.85 | 160 | 0.3857 | 18.1092 |
70
+ | 0.0695 | 5.15 | 170 | 0.3861 | 19.0413 |
71
+ | 0.0467 | 5.45 | 180 | 0.3913 | 18.5087 |
72
+ | 0.0467 | 5.76 | 190 | 0.3963 | 18.7750 |
73
+ | 0.0346 | 6.06 | 200 | 0.3967 | 18.3755 |
74
 
75
 
76
  ### Framework versions