Hugging Face's logo

TheRamsay
/
wav2vec2-ctc

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
TheRamsay commited on
Commit
8d66257
·
verified ·
1 Parent(s): 01a8756

Training in progress, epoch 0

Browse files
Files changed (3) hide show
  1. README.md +23 -5
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -4,6 +4,8 @@ license: cc-by-nc-sa-4.0
4
  base_model: fav-kky/wav2vec2-base-cs-80k-ClTRUS
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: wav2vec2-ctc
9
  results: []
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
15
  # wav2vec2-ctc
16
 
17
  This model is a fine-tuned version of [fav-kky/wav2vec2-base-cs-80k-ClTRUS](https://huggingface.co/fav-kky/wav2vec2-base-cs-80k-ClTRUS) on an unknown dataset.
 
 
 
18
 
19
  ## Model description
20
 
@@ -33,20 +38,33 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 1e-05
37
- - train_batch_size: 16
38
- - eval_batch_size: 16
39
  - seed: 42
40
  - gradient_accumulation_steps: 2
41
- - total_train_batch_size: 32
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_ratio: 0.3
45
- - num_epochs: 20
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
 
51
 
52
  ### Framework versions
 
4
  base_model: fav-kky/wav2vec2-base-cs-80k-ClTRUS
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: wav2vec2-ctc
11
  results: []
 
17
  # wav2vec2-ctc
18
 
19
  This model is a fine-tuned version of [fav-kky/wav2vec2-base-cs-80k-ClTRUS](https://huggingface.co/fav-kky/wav2vec2-base-cs-80k-ClTRUS) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 6.0118
22
+ - Wer: 1.0817
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
+ - train_batch_size: 4
43
+ - eval_batch_size: 4
44
  - seed: 42
45
  - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 8
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.3
50
+ - num_epochs: 60
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
57
+ | 3.1319 | 5.3333 | 2000 | 3.3683 | 1.0 |
58
+ | 2.2224 | 10.6667 | 4000 | 2.7979 | 1.0 |
59
+ | 1.7975 | 16.0 | 6000 | 2.8611 | 1.0054 |
60
+ | 1.4021 | 21.3333 | 8000 | 3.2493 | 1.0107 |
61
+ | 1.0624 | 26.6667 | 10000 | 3.8083 | 1.0402 |
62
+ | 0.8147 | 32.0 | 12000 | 4.1691 | 1.0683 |
63
+ | 0.6345 | 37.3333 | 14000 | 4.8640 | 1.0723 |
64
+ | 0.5284 | 42.6667 | 16000 | 5.3956 | 1.0790 |
65
+ | 0.4613 | 48.0 | 18000 | 5.5666 | 1.0924 |
66
+ | 0.4049 | 53.3333 | 20000 | 5.9451 | 1.0723 |
67
+ | 0.3765 | 58.6667 | 22000 | 6.0118 | 1.0817 |
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:548ed4b95ea5b902e4e1a661fa7b38bb0a27767836166f3cfd6d83f7bc2d9c16
3
  size 64998708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba10817121b568323cfb79a70465464b84be19faed60c776feb1518c85d146bf
3
  size 64998708
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90038c0fc2656f331005268e5bcd90aad755a09be99dbe75ab03240634580813
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645378b4b908e9fa695a23738e6016cd0d30859443ab70145629cf8462e49b47
3
  size 5176