Hugging Face's logo

KasuleTrevor
/
wav2vec2-large-sw-cv-100hr-v3

Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
KasuleTrevor commited on
Commit
7f2477a
•
1 Parent(s): cb62ccd

End of training

Browse files
Files changed (2) hide show
  1. README.md +22 -20
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
- base_model: facebook/wav2vec2-large
3
  license: apache-2.0
4
- metrics:
5
- - wer
6
  tags:
7
  - generated_from_trainer
 
 
8
  model-index:
9
  - name: wav2vec2-large-sw-cv-100hr-v3
10
  results: []
@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.8721
21
- - Model Preparation Time: 0.0042
22
- - Wer: 0.9997
23
- - Cer: 0.9176
24
 
25
  ## Model description
26
 
@@ -39,7 +39,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 0.0001
43
  - train_batch_size: 16
44
  - eval_batch_size: 8
45
  - seed: 42
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
47
  - total_train_batch_size: 32
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - lr_scheduler_warmup_ratio: 0.1
51
  - num_epochs: 120
52
  - mixed_precision_training: Native AMP
53
 
@@ -55,17 +55,19 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
57
  |:-------------:|:-------:|:-----:|:---------------:|:----------------------:|:------:|:------:|
58
- | 4.0159 | 0.9998 | 2079 | 2.7894 | 0.0042 | 0.9999 | 0.9048 |
59
- | 2.8122 | 2.0 | 4159 | 2.8360 | 0.0042 | 1.0 | 1.0 |
60
- | 2.8312 | 2.9998 | 6238 | 2.8331 | 0.0042 | 1.0 | 1.0 |
61
- | 2.8295 | 4.0 | 8318 | 2.8340 | 0.0042 | 1.0 | 1.0 |
62
- | 2.8306 | 4.9998 | 10397 | 2.8309 | 0.0042 | 1.0 | 1.0 |
63
- | 2.8301 | 6.0 | 12477 | 2.8451 | 0.0042 | 1.0 | 1.0 |
64
- | 2.8305 | 6.9998 | 14556 | 2.8320 | 0.0042 | 1.0 | 1.0 |
65
- | 2.8547 | 8.0 | 16636 | 2.8626 | 0.0042 | 1.0 | 1.0 |
66
- | 2.8611 | 8.9998 | 18715 | 2.8569 | 0.0042 | 1.0 | 1.0 |
67
- | 2.8596 | 10.0 | 20795 | 2.8573 | 0.0042 | 1.0 | 1.0 |
68
- | 2.861 | 10.9998 | 22874 | 2.8570 | 0.0042 | 1.0 | 1.0 |
 
 
69
 
70
 
71
  ### Framework versions
 
1
  ---
 
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-large
 
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: wav2vec2-large-sw-cv-100hr-v3
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6016
21
+ - Model Preparation Time: 0.0041
22
+ - Wer: 0.4019
23
+ - Cer: 0.1436
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 0.0005
43
  - train_batch_size: 16
44
  - eval_batch_size: 8
45
  - seed: 42
 
47
  - total_train_batch_size: 32
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_ratio: 0.15
51
  - num_epochs: 120
52
  - mixed_precision_training: Native AMP
53
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
57
  |:-------------:|:-------:|:-----:|:---------------:|:----------------------:|:------:|:------:|
58
+ | 1.6262 | 0.9998 | 2079 | 0.5262 | 0.0041 | 0.5289 | 0.1392 |
59
+ | 0.3281 | 2.0 | 4159 | 0.4055 | 0.0041 | 0.4037 | 0.1134 |
60
+ | 0.265 | 2.9998 | 6238 | 0.3537 | 0.0041 | 0.3599 | 0.0974 |
61
+ | 0.2592 | 4.0 | 8318 | 0.3882 | 0.0041 | 0.3790 | 0.1157 |
62
+ | 0.27 | 4.9998 | 10397 | 0.4337 | 0.0041 | 0.3919 | 0.1124 |
63
+ | 0.3063 | 6.0 | 12477 | 0.4226 | 0.0041 | 0.4094 | 0.1204 |
64
+ | 2.7704 | 6.9998 | 14556 | 2.8607 | 0.0041 | 1.0 | 1.0 |
65
+ | 2.86 | 8.0 | 16636 | 2.8618 | 0.0041 | 1.0 | 1.0 |
66
+ | 2.861 | 8.9998 | 18715 | 2.8596 | 0.0041 | 1.0 | 1.0 |
67
+ | 2.8597 | 10.0 | 20795 | 2.8618 | 0.0041 | 1.0 | 1.0 |
68
+ | 2.8611 | 10.9998 | 22874 | 2.8581 | 0.0041 | 1.0 | 1.0 |
69
+ | 2.8597 | 12.0 | 24954 | 2.8571 | 0.0041 | 1.0 | 1.0 |
70
+ | 2.861 | 12.9998 | 27033 | 2.8568 | 0.0041 | 1.0 | 1.0 |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92c8bb36fd75f2bcbe307a93484511ca2ff11f67b1d191fbcf42e627bba63adc
3
  size 1261893268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc20771142e97f4c464748b46984556075f33c25cf1e5bf2e36e9c2e4bdb38e0
3
  size 1261893268