Hugging Face's logo

jcrkn
/
wav2vec2-large-xls-r-300m-breton-colab_batch

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
jcrkn commited on
Commit
0767d52
•
1 Parent(s): a1bfb4f

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -10
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.6405002405002405
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.8613
36
- - Wer: 0.6405
37
 
38
  ## Model description
39
 
@@ -53,24 +53,24 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0003
56
- - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
- - total_train_batch_size: 16
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_steps: 250
64
  - num_epochs: 4
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 5.921 | 0.84 | 250 | 2.9989 | 1.0 |
71
- | 1.7514 | 1.68 | 500 | 1.2574 | 0.8484 |
72
- | 0.9455 | 2.52 | 750 | 0.9508 | 0.7119 |
73
- | 0.674 | 3.36 | 1000 | 0.8613 | 0.6405 |
74
 
75
 
76
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.751034151034151
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.0089
36
+ - Wer: 0.7510
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0003
56
+ - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 32
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 125
64
  - num_epochs: 4
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 7.2591 | 0.84 | 125 | 3.0754 | 1.0 |
71
+ | 2.9952 | 1.68 | 250 | 2.8232 | 1.0 |
72
+ | 1.9197 | 2.52 | 375 | 1.3326 | 0.8705 |
73
+ | 1.0542 | 3.36 | 500 | 1.0089 | 0.7510 |
74
 
75
 
76
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9c2fbbd23af4b47a11b517f370cd35370464a8a5f8a076ff4a09239c1aff063
3
  size 1262078125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05544c458e0008da3abd79c4c17a3e4c6736105a0bf46480fd2449c861754bb6
3
  size 1262078125