Hugging Face's logo

EzraWilliam
/
wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod7

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
EzraWilliam commited on
Commit
b3f4ae0
•
1 Parent(s): bcaa478

End of training

Browse files
Files changed (3) hide show
  1. README.md +27 -25
  2. model.safetensors +1 -1
  3. runs/Mar22_09-51-03_8b723128d2e2/events.out.tfevents.1711101096.8b723128d2e2.2711.0 +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
  - xtreme_s
8
  metrics:
@@ -11,8 +11,8 @@ model-index:
11
  - name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod7
12
  results:
13
  - task:
14
- type: automatic-speech-recognition
15
  name: Automatic Speech Recognition
 
16
  dataset:
17
  name: xtreme_s
18
  type: xtreme_s
@@ -20,9 +20,9 @@ model-index:
20
  split: test
21
  args: fleurs.id_id
22
  metrics:
23
- - type: wer
24
- value: 0.5133213590779824
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 xtreme_s dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.1411
36
- - Wer: 0.5133
37
 
38
  ## Model description
39
 
@@ -53,35 +53,37 @@ More information needed
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: 600
64
- - num_epochs: 180
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Wer |
70
- |:-------------:|:------:|:----:|:---------------:|:------:|
71
- | 4.9813 | 18.18 | 300 | 2.8480 | 1.0 |
72
- | 1.5729 | 36.36 | 600 | 0.8808 | 0.7159 |
73
- | 0.219 | 54.55 | 900 | 0.9209 | 0.5983 |
74
- | 0.1213 | 72.73 | 1200 | 0.9869 | 0.6005 |
75
- | 0.0898 | 90.91 | 1500 | 1.0485 | 0.5840 |
76
- | 0.0668 | 109.09 | 1800 | 1.0746 | 0.5514 |
77
- | 0.0499 | 127.27 | 2100 | 1.0648 | 0.5341 |
78
- | 0.0372 | 145.45 | 2400 | 1.1656 | 0.5280 |
79
- | 0.0292 | 163.64 | 2700 | 1.1411 | 0.5133 |
 
 
80
 
81
 
82
  ### Framework versions
83
 
84
- - Transformers 4.37.2
85
- - Pytorch 2.2.0+cu121
86
- - Datasets 2.16.1
87
- - Tokenizers 0.15.1
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
 
6
  datasets:
7
  - xtreme_s
8
  metrics:
 
11
  - name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod7
12
  results:
13
  - task:
 
14
  name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
  dataset:
17
  name: xtreme_s
18
  type: xtreme_s
 
20
  split: test
21
  args: fleurs.id_id
22
  metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.5032929202215237
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 xtreme_s dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.0673
36
+ - Wer: 0.5033
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.001
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: 600
64
+ - num_epochs: 90
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
71
+ | 5.2829 | 7.79 | 300 | 2.8538 | 1.0 |
72
+ | 1.9733 | 15.58 | 600 | 0.8923 | 0.7851 |
73
+ | 0.4186 | 23.38 | 900 | 0.8297 | 0.6443 |
74
+ | 0.2077 | 31.17 | 1200 | 0.8573 | 0.6011 |
75
+ | 0.1535 | 38.96 | 1500 | 0.9490 | 0.5800 |
76
+ | 0.1163 | 46.75 | 1800 | 1.0380 | 0.5652 |
77
+ | 0.1001 | 54.55 | 2100 | 0.9354 | 0.5417 |
78
+ | 0.0845 | 62.34 | 2400 | 1.0226 | 0.5364 |
79
+ | 0.0711 | 70.13 | 2700 | 1.0799 | 0.5220 |
80
+ | 0.0588 | 77.92 | 3000 | 1.0550 | 0.5050 |
81
+ | 0.0492 | 85.71 | 3300 | 1.0673 | 0.5033 |
82
 
83
 
84
  ### Framework versions
85
 
86
+ - Transformers 4.39.0
87
+ - Pytorch 2.2.1+cu121
88
+ - Datasets 2.18.0
89
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2483f5b5db6b5f56037c6b7acd6c014c3837cc10789c1e7fb5e8eb718eb8ccc2
3
  size 1262073980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0548df6da7dc096ea6455fa41b3a2aecd297b9b2afa10c18d35974780c33b2a
3
  size 1262073980
runs/Mar22_09-51-03_8b723128d2e2/events.out.tfevents.1711101096.8b723128d2e2.2711.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90af85ac882cf37fb093cf1bd90643e62a0ec2ddd01f66e2cefd3223c0be2e03
3
- size 12206
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186c7958a61930a226cd6768a7864514a54617da06f9aa0c5dbd6a52d0953528
3
+ size 12560