Hugging Face's logo

EzraWilliam
/
wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod17

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
EzraWilliam commited on
Commit
3c4418b
•
1 Parent(s): dd043e2

End of training

Browse files
Files changed (3) hide show
  1. README.md +20 -20
  2. model.safetensors +1 -1
  3. runs/Apr24_14-11-53_a166a9162e94/events.out.tfevents.1713968031.a166a9162e94.292.0 +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-xls-r-300m
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_Prod17
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: 0.3124539085545723
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-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: 0.3690
36
- - Wer: 0.3125
37
 
38
  ## Model description
39
 
@@ -65,23 +65,23 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
- | 2.9121 | 1.0 | 278 | 2.8104 | 1.0 |
69
- | 0.7904 | 2.0 | 556 | 0.5906 | 0.5911 |
70
- | 0.4628 | 3.0 | 834 | 0.4488 | 0.5157 |
71
- | 0.3279 | 4.0 | 1112 | 0.4175 | 0.4261 |
72
- | 0.253 | 5.0 | 1390 | 0.3738 | 0.3929 |
73
- | 0.1969 | 6.0 | 1668 | 0.3810 | 0.3847 |
74
- | 0.1657 | 7.0 | 1946 | 0.3701 | 0.3587 |
75
- | 0.1444 | 8.0 | 2224 | 0.3681 | 0.3457 |
76
- | 0.1305 | 9.0 | 2502 | 0.3632 | 0.3229 |
77
- | 0.1179 | 10.0 | 2780 | 0.3620 | 0.3225 |
78
- | 0.1037 | 11.0 | 3058 | 0.3697 | 0.3136 |
79
- | 0.0988 | 12.0 | 3336 | 0.3690 | 0.3125 |
80
 
81
 
82
  ### Framework versions
83
 
84
- - Transformers 4.40.0
85
  - Pytorch 2.2.2+cu121
86
  - Datasets 2.19.0
87
  - Tokenizers 0.19.1
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
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_Prod17
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: 0.3274336283185841
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: 0.3395
36
+ - Wer: 0.3274
37
 
38
  ## Model description
39
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
+ | 2.9137 | 1.0 | 278 | 2.8202 | 1.0 |
69
+ | 0.8546 | 2.0 | 556 | 0.6314 | 0.6728 |
70
+ | 0.4738 | 3.0 | 834 | 0.4380 | 0.4837 |
71
+ | 0.3338 | 4.0 | 1112 | 0.4024 | 0.4490 |
72
+ | 0.2557 | 5.0 | 1390 | 0.3622 | 0.4295 |
73
+ | 0.1972 | 6.0 | 1668 | 0.3381 | 0.3795 |
74
+ | 0.1644 | 7.0 | 1946 | 0.3632 | 0.3706 |
75
+ | 0.1442 | 8.0 | 2224 | 0.3352 | 0.3578 |
76
+ | 0.1287 | 9.0 | 2502 | 0.3441 | 0.3496 |
77
+ | 0.1122 | 10.0 | 2780 | 0.3501 | 0.3437 |
78
+ | 0.1035 | 11.0 | 3058 | 0.3389 | 0.3322 |
79
+ | 0.0961 | 12.0 | 3336 | 0.3395 | 0.3274 |
80
 
81
 
82
  ### Framework versions
83
 
84
+ - Transformers 4.40.1
85
  - Pytorch 2.2.2+cu121
86
  - Datasets 2.19.0
87
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9a2ba8f838de7037592dd58287a8f1af67d6a5a42161c5d81649f59dca943b0
3
  size 1261991980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bef0177bd99aa0bdc022e8257a1e62b1f5bf267bddb9b7732b648994bba9d5b
3
  size 1261991980
runs/Apr24_14-11-53_a166a9162e94/events.out.tfevents.1713968031.a166a9162e94.292.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f67482c68b6d0ec36b9a2412857574ad1a75e1d452b0c4838741a6e5ee96315b
3
- size 15751
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7838bd62361ff371fbe9b4d602f243683d3c8485669b8123902ba32d20af92
3
+ size 17374