mirfan899 commited on
Commit
c8b03a0
1 Parent(s): 1ce9595

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -47
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: 14.2905
18
- - Cer: 1.0
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 4e-55
38
  - train_batch_size: 2
39
  - eval_batch_size: 8
40
  - seed: 42
@@ -44,53 +44,53 @@ The following hyperparameters were used during training:
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss | Cer |
48
- |:-------------:|:-----:|:-----:|:---------------:|:---:|
49
- | 6.6387 | 0.74 | 500 | 14.2905 | 1.0 |
50
- | 6.7215 | 1.48 | 1000 | 14.2905 | 1.0 |
51
- | 6.6215 | 2.22 | 1500 | 14.2905 | 1.0 |
52
- | 6.5914 | 2.96 | 2000 | 14.2905 | 1.0 |
53
- | 6.8135 | 3.7 | 2500 | 14.2905 | 1.0 |
54
- | 6.5716 | 4.44 | 3000 | 14.2905 | 1.0 |
55
- | 6.6272 | 5.19 | 3500 | 14.2905 | 1.0 |
56
- | 6.6394 | 5.93 | 4000 | 14.2905 | 1.0 |
57
- | 6.6572 | 6.67 | 4500 | 14.2905 | 1.0 |
58
- | 6.5405 | 7.41 | 5000 | 14.2905 | 1.0 |
59
- | 6.7215 | 8.15 | 5500 | 14.2905 | 1.0 |
60
- | 6.6013 | 8.89 | 6000 | 14.2905 | 1.0 |
61
- | 6.666 | 9.63 | 6500 | 14.2905 | 1.0 |
62
- | 6.5773 | 10.37 | 7000 | 14.2905 | 1.0 |
63
- | 6.8272 | 11.11 | 7500 | 14.2905 | 1.0 |
64
- | 6.6015 | 11.85 | 8000 | 14.2905 | 1.0 |
65
- | 6.6827 | 12.59 | 8500 | 14.2905 | 1.0 |
66
- | 6.5923 | 13.33 | 9000 | 14.2905 | 1.0 |
67
- | 6.6176 | 14.07 | 9500 | 14.2905 | 1.0 |
68
- | 6.6977 | 14.81 | 10000 | 14.2905 | 1.0 |
69
- | 6.712 | 15.56 | 10500 | 14.2905 | 1.0 |
70
- | 6.5061 | 16.3 | 11000 | 14.2905 | 1.0 |
71
- | 6.7086 | 17.04 | 11500 | 14.2905 | 1.0 |
72
- | 6.6407 | 17.78 | 12000 | 14.2905 | 1.0 |
73
- | 6.7531 | 18.52 | 12500 | 14.2905 | 1.0 |
74
- | 6.5844 | 19.26 | 13000 | 14.2905 | 1.0 |
75
- | 6.6102 | 20.0 | 13500 | 14.2905 | 1.0 |
76
- | 6.6593 | 20.74 | 14000 | 14.2905 | 1.0 |
77
- | 6.6405 | 21.48 | 14500 | 14.2905 | 1.0 |
78
- | 6.6198 | 22.22 | 15000 | 14.2905 | 1.0 |
79
- | 6.6925 | 22.96 | 15500 | 14.2905 | 1.0 |
80
- | 6.6277 | 23.7 | 16000 | 14.2905 | 1.0 |
81
- | 6.719 | 24.44 | 16500 | 14.2905 | 1.0 |
82
- | 6.6951 | 25.19 | 17000 | 14.2905 | 1.0 |
83
- | 6.6291 | 25.93 | 17500 | 14.2905 | 1.0 |
84
- | 6.5456 | 26.67 | 18000 | 14.2905 | 1.0 |
85
- | 6.655 | 27.41 | 18500 | 14.2905 | 1.0 |
86
- | 6.6637 | 28.15 | 19000 | 14.2905 | 1.0 |
87
- | 6.6484 | 28.89 | 19500 | 14.2905 | 1.0 |
88
- | 6.6542 | 29.63 | 20000 | 14.2905 | 1.0 |
89
 
90
 
91
  ### Framework versions
92
 
93
- - Transformers 4.30.1
94
  - Pytorch 2.0.0
95
- - Datasets 2.12.0
96
  - Tokenizers 0.13.3
 
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: 0.5405
18
+ - Cer: 0.2770
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 4e-05
38
  - train_batch_size: 2
39
  - eval_batch_size: 8
40
  - seed: 42
 
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
48
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
49
+ | 3.2595 | 0.74 | 500 | 3.7094 | 1.0 |
50
+ | 2.8393 | 1.48 | 1000 | 3.2563 | 1.0 |
51
+ | 2.7916 | 2.22 | 1500 | 3.0450 | 1.0 |
52
+ | 1.9585 | 2.96 | 2000 | 1.0280 | 0.8428 |
53
+ | 1.0099 | 3.7 | 2500 | 0.6477 | 0.5162 |
54
+ | 0.7968 | 4.44 | 3000 | 0.5551 | 0.4592 |
55
+ | 0.6977 | 5.19 | 3500 | 0.5107 | 0.4065 |
56
+ | 0.609 | 5.93 | 4000 | 0.4763 | 0.3916 |
57
+ | 0.5941 | 6.67 | 4500 | 0.4817 | 0.3850 |
58
+ | 0.5411 | 7.41 | 5000 | 0.4755 | 0.3639 |
59
+ | 0.5021 | 8.15 | 5500 | 0.4649 | 0.3622 |
60
+ | 0.4884 | 8.89 | 6000 | 0.4630 | 0.3569 |
61
+ | 0.4484 | 9.63 | 6500 | 0.4675 | 0.3420 |
62
+ | 0.4432 | 10.37 | 7000 | 0.4192 | 0.3402 |
63
+ | 0.399 | 11.11 | 7500 | 0.4508 | 0.3310 |
64
+ | 0.4215 | 11.85 | 8000 | 0.4406 | 0.3345 |
65
+ | 0.366 | 12.59 | 8500 | 0.4620 | 0.3248 |
66
+ | 0.3708 | 13.33 | 9000 | 0.4594 | 0.3327 |
67
+ | 0.3352 | 14.07 | 9500 | 0.4649 | 0.3121 |
68
+ | 0.3468 | 14.81 | 10000 | 0.4413 | 0.3020 |
69
+ | 0.3283 | 15.56 | 10500 | 0.4948 | 0.2915 |
70
+ | 0.3222 | 16.3 | 11000 | 0.4870 | 0.3025 |
71
+ | 0.3081 | 17.04 | 11500 | 0.4779 | 0.2919 |
72
+ | 0.3099 | 17.78 | 12000 | 0.4927 | 0.2871 |
73
+ | 0.2485 | 18.52 | 12500 | 0.5013 | 0.2831 |
74
+ | 0.3163 | 19.26 | 13000 | 0.4929 | 0.2888 |
75
+ | 0.2555 | 20.0 | 13500 | 0.5234 | 0.2888 |
76
+ | 0.2705 | 20.74 | 14000 | 0.5259 | 0.2818 |
77
+ | 0.2632 | 21.48 | 14500 | 0.5105 | 0.2831 |
78
+ | 0.2374 | 22.22 | 15000 | 0.5284 | 0.2845 |
79
+ | 0.2565 | 22.96 | 15500 | 0.5237 | 0.2875 |
80
+ | 0.2394 | 23.7 | 16000 | 0.5368 | 0.2818 |
81
+ | 0.2458 | 24.44 | 16500 | 0.5386 | 0.2814 |
82
+ | 0.2383 | 25.19 | 17000 | 0.5366 | 0.2788 |
83
+ | 0.2152 | 25.93 | 17500 | 0.5320 | 0.2770 |
84
+ | 0.231 | 26.67 | 18000 | 0.5441 | 0.2779 |
85
+ | 0.2061 | 27.41 | 18500 | 0.5448 | 0.2796 |
86
+ | 0.245 | 28.15 | 19000 | 0.5413 | 0.2796 |
87
+ | 0.2119 | 28.89 | 19500 | 0.5379 | 0.2774 |
88
+ | 0.2155 | 29.63 | 20000 | 0.5405 | 0.2770 |
89
 
90
 
91
  ### Framework versions
92
 
93
+ - Transformers 4.30.2
94
  - Pytorch 2.0.0
95
+ - Datasets 2.13.0
96
  - Tokenizers 0.13.3