Hugging Face's logo

MubarakB
/
wav2vec2-large-xls-r-300m-zu-1hr-v1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
zl
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
MubarakB commited on
Commit
30491d8
·
verified ·
1 Parent(s): c78181f

Model save

Browse files
Files changed (2) hide show
  1. README.md +11 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
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: 3.0198
21
  - Wer: 1.0
22
- - Cer: 1.0
23
 
24
  ## Model description
25
 
@@ -38,7 +38,7 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 1e-05
42
  - train_batch_size: 16
43
  - eval_batch_size: 8
44
  - seed: 42
@@ -46,18 +46,18 @@ The following hyperparameters were used during training:
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_steps: 1000
50
- - num_epochs: 30
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
56
- |:-------------:|:------:|:----:|:---------------:|:---:|:---:|
57
- | No log | 0.9231 | 6 | 6.2030 | 1.0 | 1.0 |
58
- | No log | 2.0 | 13 | 3.3458 | 1.0 | 1.0 |
59
- | No log | 2.9231 | 19 | 3.0615 | 1.0 | 1.0 |
60
- | No log | 4.0 | 26 | 3.0198 | 1.0 | 1.0 |
61
 
62
 
63
  ### Framework versions
 
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: 23.3411
21
  - Wer: 1.0
22
+ - Cer: 1.5012
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
  - train_batch_size: 16
43
  - eval_batch_size: 8
44
  - seed: 42
 
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_steps: 500
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
+ | No log | 0.9231 | 6 | 23.3703 | 1.0 | 1.4645 |
58
+ | No log | 2.0 | 13 | 23.3671 | 1.0 | 1.4680 |
59
+ | No log | 2.9231 | 19 | 23.3600 | 1.0 | 1.4756 |
60
+ | No log | 4.0 | 26 | 23.3411 | 1.0 | 1.5012 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8d3149e3d07de6a6c74ef9d839bfa39f2d6c45bc115958c9f1b80ddb3fe3c60
3
  size 1262008380
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de9bda3b0d230f6463e2a5849330450650dbb2eef7489a70b22c866a422aa59
3
  size 1262008380