Hugging Face's logo

aconeil
/
w2v2-lmk_updated_auto

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
aconeil commited on
Commit
63d6857
·
verified ·
1 Parent(s): 39b8df9

End of training

Browse files
Files changed (3) hide show
  1. README.md +27 -27
  2. model.safetensors +1 -1
  3. runs/Nov21_15-30-28_x1001c1s7b0n1/events.out.tfevents.1763757035.x1001c1s7b0n1.481541.0 +2 -2
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Wer
25
  type: wer
26
- value: 0.686411149825784
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the audiofolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 2.3070
37
- - Wer: 0.6864
38
- - Cer: 0.2902
39
 
40
  ## Model description
41
 
@@ -54,7 +54,7 @@ More information needed
54
  ### Training hyperparameters
55
 
56
  The following hyperparameters were used during training:
57
- - learning_rate: 0.0003
58
  - train_batch_size: 8
59
  - eval_batch_size: 8
60
  - seed: 42
@@ -62,7 +62,7 @@ The following hyperparameters were used during training:
62
  - total_train_batch_size: 16
63
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
64
  - lr_scheduler_type: linear
65
- - lr_scheduler_warmup_steps: 500
66
  - num_epochs: 100
67
  - mixed_precision_training: Native AMP
68
 
@@ -70,27 +70,27 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
72
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
73
- | 5.8409 | 4.7619 | 100 | 3.1721 | 1.0 | 1.0 |
74
- | 3.0976 | 9.5238 | 200 | 2.9142 | 1.0 | 1.0 |
75
- | 2.9258 | 14.2857 | 300 | 2.8805 | 1.0 | 1.0 |
76
- | 2.7105 | 19.0476 | 400 | 2.4015 | 1.0 | 0.8926 |
77
- | 1.6379 | 23.8095 | 500 | 1.4195 | 0.8885 | 0.4029 |
78
- | 1.0008 | 28.5714 | 600 | 1.5497 | 0.8084 | 0.3884 |
79
- | 0.7061 | 33.3333 | 700 | 1.6118 | 0.7735 | 0.3290 |
80
- | 0.511 | 38.0952 | 800 | 1.8025 | 0.7526 | 0.3145 |
81
- | 0.4245 | 42.8571 | 900 | 1.8402 | 0.7526 | 0.3062 |
82
- | 0.3233 | 47.6190 | 1000 | 1.9139 | 0.7561 | 0.3077 |
83
- | 0.2793 | 52.3810 | 1100 | 1.9201 | 0.7422 | 0.3130 |
84
- | 0.2177 | 57.1429 | 1200 | 2.0397 | 0.7491 | 0.3145 |
85
- | 0.1753 | 61.9048 | 1300 | 2.1653 | 0.7317 | 0.3077 |
86
- | 0.1636 | 66.6667 | 1400 | 2.1610 | 0.7247 | 0.3214 |
87
- | 0.1545 | 71.4286 | 1500 | 2.3378 | 0.7143 | 0.3199 |
88
- | 0.1238 | 76.1905 | 1600 | 2.2300 | 0.7108 | 0.3161 |
89
- | 0.1148 | 80.9524 | 1700 | 2.2409 | 0.6934 | 0.2963 |
90
- | 0.0961 | 85.7143 | 1800 | 2.2434 | 0.6829 | 0.2925 |
91
- | 0.0938 | 90.4762 | 1900 | 2.2213 | 0.6969 | 0.3008 |
92
- | 0.0815 | 95.2381 | 2000 | 2.2775 | 0.6969 | 0.3008 |
93
- | 0.0852 | 100.0 | 2100 | 2.3070 | 0.6864 | 0.2902 |
94
 
95
 
96
  ### Framework versions
 
23
  metrics:
24
  - name: Wer
25
  type: wer
26
+ value: 0.5923344947735192
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the audiofolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.3904
37
+ - Wer: 0.5923
38
+ - Cer: 0.2399
39
 
40
  ## Model description
41
 
 
54
  ### Training hyperparameters
55
 
56
  The following hyperparameters were used during training:
57
+ - learning_rate: 0.0001
58
  - train_batch_size: 8
59
  - eval_batch_size: 8
60
  - seed: 42
 
62
  - total_train_batch_size: 16
63
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
64
  - lr_scheduler_type: linear
65
+ - lr_scheduler_warmup_steps: 300
66
  - num_epochs: 100
67
  - mixed_precision_training: Native AMP
68
 
 
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
72
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
73
+ | 8.4649 | 4.7619 | 100 | 4.0812 | 1.0 | 1.0 |
74
+ | 3.2496 | 9.5238 | 200 | 2.9563 | 1.0 | 1.0 |
75
+ | 2.9748 | 14.2857 | 300 | 2.9203 | 1.0 | 1.0 |
76
+ | 2.8994 | 19.0476 | 400 | 2.8260 | 1.0 | 1.0 |
77
+ | 2.5637 | 23.8095 | 500 | 2.1752 | 1.0 | 0.8309 |
78
+ | 1.8029 | 28.5714 | 600 | 1.4903 | 0.9861 | 0.5156 |
79
+ | 1.4084 | 33.3333 | 700 | 1.2974 | 0.9164 | 0.3869 |
80
+ | 1.1087 | 38.0952 | 800 | 1.2984 | 0.7387 | 0.2856 |
81
+ | 0.9667 | 42.8571 | 900 | 1.2944 | 0.6794 | 0.2727 |
82
+ | 0.8039 | 47.6190 | 1000 | 1.3522 | 0.6481 | 0.2681 |
83
+ | 0.7177 | 52.3810 | 1100 | 1.2763 | 0.5993 | 0.2353 |
84
+ | 0.6455 | 57.1429 | 1200 | 1.2724 | 0.6446 | 0.2475 |
85
+ | 0.5526 | 61.9048 | 1300 | 1.3468 | 0.6411 | 0.2483 |
86
+ | 0.5185 | 66.6667 | 1400 | 1.3384 | 0.6167 | 0.2414 |
87
+ | 0.498 | 71.4286 | 1500 | 1.3211 | 0.6098 | 0.2475 |
88
+ | 0.4556 | 76.1905 | 1600 | 1.3733 | 0.6272 | 0.2430 |
89
+ | 0.4398 | 80.9524 | 1700 | 1.4148 | 0.6376 | 0.2559 |
90
+ | 0.416 | 85.7143 | 1800 | 1.3720 | 0.6132 | 0.2437 |
91
+ | 0.4177 | 90.4762 | 1900 | 1.3502 | 0.5923 | 0.2407 |
92
+ | 0.4069 | 95.2381 | 2000 | 1.3766 | 0.6028 | 0.2460 |
93
+ | 0.4045 | 100.0 | 2100 | 1.3904 | 0.5923 | 0.2399 |
94
 
95
 
96
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:210256ca90c00634d4895b59e5d027b894b1873580668b66fc9b69ebada1bf73
3
  size 1261938680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ffe4e2e570493fb5a63bc2d2635358d24a4fbd7eee546cc14c89af717fd2aa0
3
  size 1261938680
runs/Nov21_15-30-28_x1001c1s7b0n1/events.out.tfevents.1763757035.x1001c1s7b0n1.481541.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5b824f09d47431f645209ebe78c21b9414daf9543ca4aaa7cd419695865e76d
3
- size 23191
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c5226d803620396ebd3bb0d1942598ba94d06fca244b39cb420a7eac398df4a
3
+ size 23545