Hugging Face's logo

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

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
jcrkn commited on
Commit
83aabd1
•
1 Parent(s): 9069789

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -12
  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: 0.7804713804713804
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: 1.3812
36
- - Wer: 0.7805
37
 
38
  ## Model description
39
 
@@ -52,29 +52,30 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.001
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: 500
64
- - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 4.1427 | 3.12 | 400 | 1.6053 | 0.9481 |
71
- | 1.1814 | 6.25 | 800 | 1.4622 | 0.8634 |
72
- | 0.5771 | 9.38 | 1200 | 1.3812 | 0.7805 |
 
73
 
74
 
75
  ### Framework versions
76
 
77
- - Transformers 4.31.0
78
  - Pytorch 2.0.1+cu118
79
  - Datasets 2.14.4
80
  - Tokenizers 0.13.3
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.794035594035594
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: 1.4386
36
+ - Wer: 0.7940
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.0009
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: 300
64
+ - num_epochs: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 0.8198 | 1.17 | 300 | 1.5223 | 0.8765 |
71
+ | 0.8458 | 2.35 | 600 | 1.4725 | 0.8534 |
72
+ | 0.6537 | 3.52 | 900 | 1.4510 | 0.8080 |
73
+ | 0.4878 | 4.7 | 1200 | 1.4386 | 0.7940 |
74
 
75
 
76
  ### Framework versions
77
 
78
+ - Transformers 4.32.0
79
  - Pytorch 2.0.1+cu118
80
  - Datasets 2.14.4
81
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a5d7a160d06473eafeea45781085b31ce628a7dd4f9ebfc1c6164baeb5d2f3d
3
  size 1262078125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8078de2c6f3bf6e14a2f9ea86fa4d53cddcfff2fdcd50f5849247f3defdd32
3
  size 1262078125