Hugging Face's logo

gweltou
/
wav2vec2-large-xlsr-53-br

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
gweltou commited on
Commit
19a21fd
•
1 Parent(s): cb59859

Model save

Browse files
Files changed (3) hide show
  1. README.md +46 -37
  2. model.safetensors +1 -1
  3. runs/Jun03_08-47-04_gweltaz-NUC10i7FNK/events.out.tfevents.1717397345.gweltaz-NUC10i7FNK.2937.0 +2 -2
README.md CHANGED
@@ -1,25 +1,40 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: facebook/wav2vec2-large-xlsr-53
 
6
  metrics:
7
  - wer
8
  model-index:
9
- - name: wav2vec2-large-xlsr-53-breton
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- # wav2vec2-large-xlsr-53-breton
17
 
18
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9840
21
- - Wer: 0.5852
22
- - Cer: 0.2130
23
 
24
  ## Model description
25
 
@@ -39,45 +54,39 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 6e-05
42
- - train_batch_size: 16
43
  - eval_batch_size: 8
44
  - seed: 42
45
- - gradient_accumulation_steps: 2
46
  - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_ratio: 0.08
50
- - num_epochs: 50
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
56
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
57
- | 11.8947 | 2.56 | 250 | 3.4769 | 1.0 | 0.9862 |
58
- | 3.1668 | 5.13 | 500 | 3.0459 | 1.0 | 0.9862 |
59
- | 2.6491 | 7.69 | 750 | 1.6416 | 0.9319 | 0.4441 |
60
- | 1.4107 | 10.26 | 1000 | 1.1000 | 0.7751 | 0.2852 |
61
- | 0.9989 | 12.82 | 1250 | 0.9827 | 0.7092 | 0.2578 |
62
- | 0.8238 | 15.38 | 1500 | 0.9543 | 0.6864 | 0.2476 |
63
- | 0.7193 | 17.95 | 1750 | 0.9241 | 0.6547 | 0.2371 |
64
- | 0.6377 | 20.51 | 2000 | 0.9296 | 0.6452 | 0.2352 |
65
- | 0.5865 | 23.08 | 2250 | 0.9287 | 0.6320 | 0.2301 |
66
- | 0.541 | 25.64 | 2500 | 0.9359 | 0.6205 | 0.2231 |
67
- | 0.4988 | 28.21 | 2750 | 0.9850 | 0.6149 | 0.2244 |
68
- | 0.4691 | 30.77 | 3000 | 0.9566 | 0.6065 | 0.2192 |
69
- | 0.4568 | 33.33 | 3250 | 0.9653 | 0.6019 | 0.2175 |
70
- | 0.4485 | 35.9 | 3500 | 0.9760 | 0.5949 | 0.2175 |
71
- | 0.4219 | 38.46 | 3750 | 0.9824 | 0.5926 | 0.2177 |
72
- | 0.397 | 41.03 | 4000 | 0.9669 | 0.5885 | 0.2138 |
73
- | 0.3912 | 43.59 | 4250 | 0.9857 | 0.5908 | 0.2145 |
74
- | 0.3764 | 46.15 | 4500 | 0.9937 | 0.5886 | 0.2145 |
75
- | 0.3742 | 48.72 | 4750 | 0.9840 | 0.5852 | 0.2130 |
76
 
77
 
78
  ### Framework versions
79
 
80
- - Transformers 4.35.2
81
- - Pytorch 2.1.0+cu121
82
- - Datasets 2.16.1
83
- - Tokenizers 0.15.0
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
6
+ datasets:
7
+ - common_voice_15_0
8
  metrics:
9
  - wer
10
  model-index:
11
+ - name: wav2vec2-large-xlsr-53-br
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice_15_0
18
+ type: common_voice_15_0
19
+ config: br
20
+ split: None
21
+ args: br
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 54.71511888739345
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
+ # wav2vec2-large-xlsr-53-br
32
 
33
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_15_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7879
36
+ - Wer: 54.7151
37
+ - Cer: 19.2493
38
 
39
  ## Model description
40
 
 
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 6e-05
57
+ - train_batch_size: 8
58
  - eval_batch_size: 8
59
  - seed: 42
60
+ - gradient_accumulation_steps: 4
61
  - total_train_batch_size: 32
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 300
65
+ - num_epochs: 30
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
71
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
72
+ | 6.3257 | 2.18 | 500 | 3.0700 | 100.0 | 99.0871 |
73
+ | 2.2071 | 4.36 | 1000 | 1.1541 | 80.0449 | 29.4230 |
74
+ | 1.0019 | 6.54 | 1500 | 0.8986 | 69.2059 | 24.3938 |
75
+ | 0.7796 | 8.71 | 2000 | 0.8015 | 63.3737 | 22.1296 |
76
+ | 0.6677 | 10.89 | 2500 | 0.8014 | 61.4984 | 21.4568 |
77
+ | 0.5937 | 13.07 | 3000 | 0.7623 | 58.9323 | 20.4929 |
78
+ | 0.5454 | 15.25 | 3500 | 0.7975 | 57.8466 | 20.2585 |
79
+ | 0.5075 | 17.43 | 4000 | 0.7831 | 56.7250 | 19.7879 |
80
+ | 0.4837 | 19.61 | 4500 | 0.7902 | 55.9623 | 19.5101 |
81
+ | 0.4529 | 21.79 | 5000 | 0.7851 | 54.9753 | 19.0924 |
82
+ | 0.4381 | 23.97 | 5500 | 0.7865 | 55.1727 | 19.3211 |
83
+ | 0.4208 | 26.14 | 6000 | 0.8168 | 55.1817 | 19.3967 |
84
+ | 0.4197 | 28.32 | 6500 | 0.7879 | 54.7151 | 19.2493 |
 
 
 
 
 
 
85
 
86
 
87
  ### Framework versions
88
 
89
+ - Transformers 4.39.1
90
+ - Pytorch 2.0.1+cu117
91
+ - Datasets 2.18.0
92
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:062d783998ef2b200d2c7094dddda6a478e6944534b38e2b56da97f0efc6c58f
3
  size 1262012432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c604794129ec1687d5ee04edcae82b445f864b30c3be119899c787a85c59eb4
3
  size 1262012432
runs/Jun03_08-47-04_gweltaz-NUC10i7FNK/events.out.tfevents.1717397345.gweltaz-NUC10i7FNK.2937.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:833f0ee3b70e655516dfbfe85ecf2e7520a579d3120753d0e7a9cf469dbdaa99
3
- size 13814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19812879513e1a20a3853cea6e6fd5e63ad5f4132b9ec49c5c0c553a77391644
3
+ size 14168