Hugging Face's logo

gweltou
/
wav2vec2-xls-r-300m-MCV15

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
gweltou commited on
Commit
0a40804
•
1 Parent(s): 3d1cb92

Model save

Browse files
Files changed (3) hide show
  1. README.md +18 -22
  2. model.safetensors +1 -1
  3. runs/Dec25_12-24-53_b6fc087a7e08/events.out.tfevents.1703507153.b6fc087a7e08.1022.0 +2 -2
README.md CHANGED
@@ -8,10 +8,6 @@ metrics:
8
  model-index:
9
  - name: wav2vec2-xls-r-300m-MCV15
10
  results: []
11
- datasets:
12
- - mozilla-foundation/common_voice_15_0
13
- language:
14
- - br
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -21,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 1.1155
25
- - Wer: 0.6060
26
- - Cer: 0.2242
27
 
28
  ## Model description
29
 
@@ -42,7 +38,7 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 8e-05
46
  - train_batch_size: 24
47
  - eval_batch_size: 8
48
  - seed: 42
@@ -58,19 +54,19 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
60
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
61
- | 9.8843 | 4.5 | 250 | 3.3243 | 1.0 | 1.0000 |
62
- | 3.066 | 9.01 | 500 | 2.8141 | 1.0 | 1.0000 |
63
- | 1.8006 | 13.51 | 750 | 1.1647 | 0.7936 | 0.3028 |
64
- | 0.8925 | 18.02 | 1000 | 1.0696 | 0.7174 | 0.2679 |
65
- | 0.6306 | 22.52 | 1250 | 1.0330 | 0.6792 | 0.2509 |
66
- | 0.512 | 27.03 | 1500 | 0.9988 | 0.6560 | 0.2405 |
67
- | 0.4275 | 31.53 | 1750 | 1.0428 | 0.6345 | 0.2332 |
68
- | 0.3837 | 36.04 | 2000 | 1.0555 | 0.6267 | 0.2315 |
69
- | 0.3481 | 40.54 | 2250 | 1.1165 | 0.6231 | 0.2312 |
70
- | 0.3081 | 45.05 | 2500 | 1.0772 | 0.6142 | 0.2255 |
71
- | 0.2906 | 49.55 | 2750 | 1.1146 | 0.6085 | 0.2267 |
72
- | 0.2923 | 54.05 | 3000 | 1.1030 | 0.6058 | 0.2228 |
73
- | 0.259 | 58.56 | 3250 | 1.1155 | 0.6060 | 0.2242 |
74
 
75
 
76
  ### Framework versions
@@ -78,4 +74,4 @@ The following hyperparameters were used during training:
78
  - Transformers 4.35.2
79
  - Pytorch 2.1.0+cu121
80
  - Datasets 2.16.0
81
- - Tokenizers 0.15.0
 
8
  model-index:
9
  - name: wav2vec2-xls-r-300m-MCV15
10
  results: []
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.9816
21
+ - Wer: 0.6048
22
+ - Cer: 0.2217
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 6e-05
42
  - train_batch_size: 24
43
  - eval_batch_size: 8
44
  - seed: 42
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
57
+ | 11.1167 | 4.5 | 250 | 3.6649 | 1.0 | 1.0000 |
58
+ | 3.1388 | 9.01 | 500 | 2.9534 | 1.0 | 1.0000 |
59
+ | 2.1614 | 13.51 | 750 | 1.3123 | 0.8240 | 0.3193 |
60
+ | 1.0783 | 18.02 | 1000 | 1.0311 | 0.7298 | 0.2684 |
61
+ | 0.7555 | 22.52 | 1250 | 0.9512 | 0.6806 | 0.2486 |
62
+ | 0.6159 | 27.03 | 1500 | 0.9362 | 0.6561 | 0.2418 |
63
+ | 0.5212 | 31.53 | 1750 | 0.9738 | 0.6409 | 0.2344 |
64
+ | 0.4684 | 36.04 | 2000 | 0.9576 | 0.6223 | 0.2282 |
65
+ | 0.4275 | 40.54 | 2250 | 0.9829 | 0.6178 | 0.2267 |
66
+ | 0.3856 | 45.05 | 2500 | 0.9753 | 0.6102 | 0.2244 |
67
+ | 0.3665 | 49.55 | 2750 | 0.9797 | 0.6058 | 0.2223 |
68
+ | 0.3668 | 54.05 | 3000 | 0.9690 | 0.6046 | 0.2217 |
69
+ | 0.3294 | 58.56 | 3250 | 0.9816 | 0.6048 | 0.2217 |
70
 
71
 
72
  ### Framework versions
 
74
  - Transformers 4.35.2
75
  - Pytorch 2.1.0+cu121
76
  - Datasets 2.16.0
77
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a769c84a24d5c050f5f32cf97fdb1c2135ae645751ce5eb36d9546367d84e2a3
3
  size 1261975580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31afcdcade5854d30c2a5201fe17c6d462699313fbf705b5af542a91836b4da5
3
  size 1261975580
runs/Dec25_12-24-53_b6fc087a7e08/events.out.tfevents.1703507153.b6fc087a7e08.1022.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad51fee6b539560e54c6d823af1c6116bbfa93b904b486aa31f61528247e2660
3
- size 11980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d089e0eadca6908f4b3f9aacf594d77cdd34e269003c0c7c4eb6e59f4df55e64
3
+ size 12856