Hugging Face's logo

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

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
jcrkn commited on
Commit
0fbe3c4
·
1 Parent(s): ca4ea93

End of training

Browse files
Files changed (2) hide show
  1. README.md +8 -11
  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: 0.5871091871091871
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: 0.8441
36
- - Wer: 0.5871
37
 
38
  ## Model description
39
 
@@ -60,20 +60,17 @@ The following hyperparameters were used during training:
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: 200
64
  - num_epochs: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 6.4369 | 0.67 | 200 | 3.0380 | 1.0 |
71
- | 2.0027 | 1.34 | 400 | 1.3767 | 0.9015 |
72
- | 1.1669 | 2.02 | 600 | 1.1571 | 0.7993 |
73
- | 0.8346 | 2.69 | 800 | 0.9745 | 0.7225 |
74
- | 0.6798 | 3.36 | 1000 | 0.8956 | 0.6571 |
75
- | 0.5319 | 4.03 | 1200 | 0.8635 | 0.6129 |
76
- | 0.4013 | 4.71 | 1400 | 0.8441 | 0.5871 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.6465608465608466
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: 0.9111
36
+ - Wer: 0.6466
37
 
38
  ## Model description
39
 
 
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
+ | 5.7652 | 1.01 | 300 | 2.2099 | 0.9951 |
71
+ | 1.3954 | 2.02 | 600 | 1.1636 | 0.8122 |
72
+ | 0.8595 | 3.03 | 900 | 0.9715 | 0.7229 |
73
+ | 0.592 | 4.03 | 1200 | 0.9111 | 0.6466 |
 
 
 
74
 
75
 
76
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4917236cdc1258a87b493d72db389f222d38906779a2cf60a918ae82e92b7c29
3
  size 1262078125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c452b91668044f2f1a4d4fed910cfc8b6ea4bb575c3c72581b9c4d214fb723
3
  size 1262078125