patrickvonplaten commited on
Commit
451c409
1 Parent(s): c82862c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -31
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [asapp/sew-mid-100k](https://huggingface.co/asapp/sew-mid-100k) on the LIBRISPEECH_ASR - CLEAN dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 3.9609
20
- - Wer: 1.0
21
 
22
  ## Model description
23
 
@@ -36,7 +36,7 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 0.0003
40
  - train_batch_size: 4
41
  - eval_batch_size: 8
42
  - seed: 42
@@ -52,34 +52,34 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:-----:|:----:|:---------------:|:---:|
57
- | 2.9558 | 0.11 | 100 | 2.9238 | 1.0 |
58
- | 2.8978 | 0.22 | 200 | 2.9614 | 1.0 |
59
- | 2.9267 | 0.34 | 300 | 3.3049 | 1.0 |
60
- | 3.1351 | 0.45 | 400 | 2.9246 | 1.0 |
61
- | 3.4365 | 0.56 | 500 | 4.2798 | 1.0 |
62
- | 3.1861 | 0.67 | 600 | 4.0740 | 1.0 |
63
- | 2.914 | 0.78 | 700 | 3.6876 | 1.0 |
64
- | 3.0777 | 0.9 | 800 | 3.7421 | 1.0 |
65
- | 2.8181 | 1.01 | 900 | 3.7825 | 1.0 |
66
- | 2.8211 | 1.12 | 1000 | 3.9630 | 1.0 |
67
- | 2.8209 | 1.23 | 1100 | 3.9605 | 1.0 |
68
- | 2.8304 | 1.35 | 1200 | 3.7005 | 1.0 |
69
- | 2.85 | 1.46 | 1300 | 3.5085 | 1.0 |
70
- | 2.8509 | 1.57 | 1400 | 3.6157 | 1.0 |
71
- | 2.8643 | 1.68 | 1500 | 3.5116 | 1.0 |
72
- | 2.8265 | 1.79 | 1600 | 3.6322 | 1.0 |
73
- | 2.8032 | 1.91 | 1700 | 4.0325 | 1.0 |
74
- | 2.8053 | 2.02 | 1800 | 4.0125 | 1.0 |
75
- | 2.819 | 2.13 | 1900 | 3.7971 | 1.0 |
76
- | 2.8163 | 2.24 | 2000 | 3.9216 | 1.0 |
77
- | 2.8214 | 2.35 | 2100 | 3.9178 | 1.0 |
78
- | 2.8116 | 2.47 | 2200 | 3.9604 | 1.0 |
79
- | 2.81 | 2.58 | 2300 | 3.9279 | 1.0 |
80
- | 2.8051 | 2.69 | 2400 | 3.9737 | 1.0 |
81
- | 2.8179 | 2.8 | 2500 | 3.9725 | 1.0 |
82
- | 2.8098 | 2.91 | 2600 | 3.9591 | 1.0 |
83
 
84
 
85
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [asapp/sew-mid-100k](https://huggingface.co/asapp/sew-mid-100k) on the LIBRISPEECH_ASR - CLEAN dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1976
20
+ - Wer: 0.1665
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
  - train_batch_size: 4
41
  - eval_batch_size: 8
42
  - seed: 42
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
57
+ | 3.4274 | 0.11 | 100 | 4.1419 | 1.0 |
58
+ | 2.9657 | 0.22 | 200 | 3.1203 | 1.0 |
59
+ | 2.9069 | 0.34 | 300 | 3.0107 | 1.0 |
60
+ | 2.8666 | 0.45 | 400 | 2.8960 | 1.0 |
61
+ | 1.4535 | 0.56 | 500 | 1.4062 | 0.8664 |
62
+ | 0.6821 | 0.67 | 600 | 0.5530 | 0.4930 |
63
+ | 0.4827 | 0.78 | 700 | 0.4122 | 0.3630 |
64
+ | 0.4485 | 0.9 | 800 | 0.3597 | 0.3243 |
65
+ | 0.2666 | 1.01 | 900 | 0.3104 | 0.2790 |
66
+ | 0.2378 | 1.12 | 1000 | 0.2913 | 0.2613 |
67
+ | 0.2516 | 1.23 | 1100 | 0.2702 | 0.2452 |
68
+ | 0.2456 | 1.35 | 1200 | 0.2619 | 0.2338 |
69
+ | 0.2392 | 1.46 | 1300 | 0.2466 | 0.2195 |
70
+ | 0.2117 | 1.57 | 1400 | 0.2379 | 0.2092 |
71
+ | 0.1837 | 1.68 | 1500 | 0.2295 | 0.2029 |
72
+ | 0.1757 | 1.79 | 1600 | 0.2240 | 0.1949 |
73
+ | 0.1626 | 1.91 | 1700 | 0.2195 | 0.1927 |
74
+ | 0.168 | 2.02 | 1800 | 0.2137 | 0.1853 |
75
+ | 0.168 | 2.13 | 1900 | 0.2123 | 0.1839 |
76
+ | 0.1576 | 2.24 | 2000 | 0.2095 | 0.1803 |
77
+ | 0.1756 | 2.35 | 2100 | 0.2075 | 0.1776 |
78
+ | 0.1467 | 2.47 | 2200 | 0.2049 | 0.1754 |
79
+ | 0.1702 | 2.58 | 2300 | 0.2013 | 0.1722 |
80
+ | 0.177 | 2.69 | 2400 | 0.1993 | 0.1701 |
81
+ | 0.1417 | 2.8 | 2500 | 0.1983 | 0.1688 |
82
+ | 0.1302 | 2.91 | 2600 | 0.1977 | 0.1678 |
83
 
84
 
85
  ### Framework versions