BALAKA commited on
Commit
d0cbbe4
1 Parent(s): 364a6ac

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -14
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 0.4557774607703281
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [airesearch/wav2vec2-large-xlsr-53-th](https://huggingface.co/airesearch/wav2vec2-large-xlsr-53-th) on the common_voice dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 1.0926
35
- - Wer: 0.4558
36
 
37
  ## Model description
38
 
@@ -58,23 +58,28 @@ The following hyperparameters were used during training:
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
  - lr_scheduler_warmup_steps: 30
61
- - num_epochs: 35
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
- | 5.4829 | 3.23 | 100 | 3.4277 | 1.0 |
69
- | 3.301 | 6.45 | 200 | 3.2260 | 1.0 |
70
- | 2.3 | 9.68 | 300 | 1.2590 | 0.5292 |
71
- | 1.1601 | 12.9 | 400 | 1.0578 | 0.5892 |
72
- | 0.9381 | 16.13 | 500 | 1.0390 | 0.4957 |
73
- | 0.8211 | 19.35 | 600 | 1.0411 | 0.4679 |
74
- | 0.7227 | 22.58 | 700 | 1.0614 | 0.4558 |
75
- | 0.6805 | 25.81 | 800 | 1.0750 | 0.4579 |
76
- | 0.6389 | 29.03 | 900 | 1.0678 | 0.4629 |
77
- | 0.6045 | 32.26 | 1000 | 1.0926 | 0.4558 |
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
 
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 0.4536376604850214
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [airesearch/wav2vec2-large-xlsr-53-th](https://huggingface.co/airesearch/wav2vec2-large-xlsr-53-th) on the common_voice dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 1.2174
35
+ - Wer: 0.4536
36
 
37
  ## Model description
38
 
 
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
  - lr_scheduler_warmup_steps: 30
61
+ - num_epochs: 50
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
+ | 5.3619 | 3.23 | 100 | 3.2891 | 1.0 |
69
+ | 3.299 | 6.45 | 200 | 3.1670 | 1.0 |
70
+ | 2.1179 | 9.68 | 300 | 1.1747 | 0.5221 |
71
+ | 1.1047 | 12.9 | 400 | 1.0323 | 0.5849 |
72
+ | 0.8974 | 16.13 | 500 | 1.0128 | 0.5029 |
73
+ | 0.769 | 19.35 | 600 | 1.0402 | 0.4957 |
74
+ | 0.6659 | 22.58 | 700 | 1.0902 | 0.4729 |
75
+ | 0.6114 | 25.81 | 800 | 1.1412 | 0.4629 |
76
+ | 0.5511 | 29.03 | 900 | 1.1156 | 0.4643 |
77
+ | 0.5137 | 32.26 | 1000 | 1.1556 | 0.4679 |
78
+ | 0.5132 | 35.48 | 1100 | 1.1851 | 0.4515 |
79
+ | 0.4583 | 38.71 | 1200 | 1.1971 | 0.4529 |
80
+ | 0.4523 | 41.94 | 1300 | 1.2182 | 0.4579 |
81
+ | 0.4329 | 45.16 | 1400 | 1.2178 | 0.4586 |
82
+ | 0.4502 | 48.39 | 1500 | 1.2174 | 0.4536 |
83
 
84
 
85
  ### Framework versions