Hugging Face's logo

EzraWilliam
/
wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod14

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
EzraWilliam commited on
Commit
2511428
•
1 Parent(s): 725988f

End of training

Browse files
Files changed (3) hide show
  1. README.md +23 -23
  2. model.safetensors +1 -1
  3. runs/Apr18_17-39-16_549c0851f499/events.out.tfevents.1713462074.549c0851f499.577.0 +2 -2
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: facebook/wav2vec2-large-xlsr-53
6
  datasets:
7
  - common_voice_13_0
8
  metrics:
@@ -11,8 +11,8 @@ model-index:
11
  - name: wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod14
12
  results:
13
  - task:
14
- type: automatic-speech-recognition
15
  name: Automatic Speech Recognition
 
16
  dataset:
17
  name: common_voice_13_0
18
  type: common_voice_13_0
@@ -20,9 +20,9 @@ model-index:
20
  split: test
21
  args: id
22
  metrics:
23
- - type: wer
24
- value: 0.9999539085545722
25
- name: Wer
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-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.9481
36
- - Wer: 1.0000
37
 
38
  ## Model description
39
 
@@ -52,8 +52,8 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.003
56
- - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -65,23 +65,23 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
- | 2.9078 | 1.0 | 556 | 2.9342 | 1.0 |
69
- | 2.875 | 2.0 | 1112 | 2.8557 | 1.0 |
70
- | 2.6528 | 3.0 | 1668 | 2.5665 | 1.0000 |
71
- | 2.386 | 4.0 | 2224 | 2.3012 | 1.0000 |
72
- | 2.3101 | 5.0 | 2780 | 2.1943 | 0.9999 |
73
- | 2.2018 | 6.0 | 3336 | 2.1332 | 1.0 |
74
- | 2.1752 | 7.0 | 3892 | 2.0791 | 1.0 |
75
- | 2.1255 | 8.0 | 4448 | 2.0347 | 1.0 |
76
- | 2.0975 | 9.0 | 5004 | 2.0129 | 1.0 |
77
- | 2.0718 | 10.0 | 5560 | 1.9677 | 1.0 |
78
- | 2.0771 | 11.0 | 6116 | 1.9591 | 1.0 |
79
- | 2.0516 | 12.0 | 6672 | 1.9481 | 1.0000 |
80
 
81
 
82
  ### Framework versions
83
 
84
- - Transformers 4.39.3
85
  - Pytorch 2.2.2+cu121
86
  - Datasets 2.18.0
87
- - Tokenizers 0.15.2
 
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_13_0
8
  metrics:
 
11
  - name: wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod14
12
  results:
13
  - task:
 
14
  name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
  dataset:
17
  name: common_voice_13_0
18
  type: common_voice_13_0
 
20
  split: test
21
  args: id
22
  metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.32789454277286134
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-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3505
36
+ - Wer: 0.3279
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.0001
56
+ - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
+ | 2.9451 | 1.0 | 278 | 2.9182 | 1.0 |
69
+ | 2.87 | 2.0 | 556 | 2.7116 | 1.0 |
70
+ | 1.1102 | 3.0 | 834 | 0.6030 | 0.5907 |
71
+ | 0.6952 | 4.0 | 1112 | 0.4691 | 0.4755 |
72
+ | 0.5976 | 5.0 | 1390 | 0.4316 | 0.4263 |
73
+ | 0.4842 | 6.0 | 1668 | 0.3887 | 0.3842 |
74
+ | 0.4444 | 7.0 | 1946 | 0.3722 | 0.3670 |
75
+ | 0.4221 | 8.0 | 2224 | 0.3721 | 0.3538 |
76
+ | 0.3929 | 9.0 | 2502 | 0.3527 | 0.3463 |
77
+ | 0.3611 | 10.0 | 2780 | 0.3538 | 0.3386 |
78
+ | 0.3669 | 11.0 | 3058 | 0.3513 | 0.3303 |
79
+ | 0.3517 | 12.0 | 3336 | 0.3505 | 0.3279 |
80
 
81
 
82
  ### Framework versions
83
 
84
+ - Transformers 4.40.0
85
  - Pytorch 2.2.2+cu121
86
  - Datasets 2.18.0
87
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b470860af4b7fc4d239bd0740df84bdf356e3fece6eeef202511db9107fa3793
3
  size 1261991980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f98d6f88e04a591ed3ecccf2a3ce79285dbb9929743c9f0a858beb1ddb4ac41
3
  size 1261991980
runs/Apr18_17-39-16_549c0851f499/events.out.tfevents.1713462074.549c0851f499.577.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e30fd76de9332cb146b5647baf0e9281a8faa817065259cb03967cce6a61d223
3
- size 15971
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a1cc7a4a62a60c10635c829e9805a0b63398c9c05a5fbab504f05f9b54b97c
3
+ size 17594