Hugging Face's logo

manhvh2601
/
whisper_data_self_tiny

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Vietnamese
whisper
VHM20191956-SpeechToText
Generated from Trainer
Model card Files
xet
Metrics Community
manhvh2601 commited on
Commit
d4328f4
·
verified ·
1 Parent(s): 28dacc8

Model save

Browse files
Files changed (3) hide show
  1. README.md +17 -20
  2. model.safetensors +1 -1
  3. runs/Jan24_11-05-32_b519fedc9610/events.out.tfevents.1706094334.b519fedc9610.15384.0 +2 -2
README.md CHANGED
@@ -1,27 +1,24 @@
1
  ---
2
- language:
3
- - vi
4
  license: apache-2.0
5
- base_model: openai/whisper-small
6
  tags:
7
- - VHM20191956-SpeechToText
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: Whisper Vietnamese Vu Hoang Manh
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # Whisper Vietnamese Vu Hoang Manh
20
 
21
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Vietnamese ASR dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0233
24
- - Wer: 28.8050
25
 
26
  ## Model description
27
 
@@ -40,7 +37,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 6e-06
44
  - train_batch_size: 16
45
  - eval_batch_size: 8
46
  - seed: 42
@@ -54,16 +51,16 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
- | 0.1968 | 1.0 | 105 | 0.0819 | 25.7610 |
58
- | 0.0749 | 2.0 | 210 | 0.0325 | 17.9256 |
59
- | 0.0194 | 3.0 | 315 | 0.0231 | 18.4893 |
60
- | 0.0145 | 4.0 | 420 | 0.0206 | 22.7170 |
61
- | 0.0068 | 5.0 | 525 | 0.0219 | 18.3766 |
62
- | 0.005 | 6.0 | 630 | 0.0237 | 20.4059 |
63
- | 0.0069 | 7.0 | 735 | 0.0218 | 24.8027 |
64
- | 0.0037 | 8.0 | 840 | 0.0233 | 26.0428 |
65
- | 0.0013 | 9.0 | 945 | 0.0231 | 26.6065 |
66
- | 0.0009 | 10.0 | 1050 | 0.0233 | 28.8050 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
 
 
2
  license: apache-2.0
3
+ base_model: openai/whisper-tiny
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
8
  model-index:
9
+ - name: whisper_data_self_tiny
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # whisper_data_self_tiny
17
 
18
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0159
21
+ - Wer: 25.6483
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 8e-06
41
  - train_batch_size: 16
42
  - eval_batch_size: 8
43
  - seed: 42
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
54
+ | 0.1249 | 1.0 | 105 | 0.0589 | 23.9008 |
55
+ | 0.0557 | 2.0 | 210 | 0.0235 | 14.4307 |
56
+ | 0.0143 | 3.0 | 315 | 0.0181 | 19.0530 |
57
+ | 0.011 | 4.0 | 420 | 0.0172 | 22.3788 |
58
+ | 0.0043 | 5.0 | 525 | 0.0161 | 21.2514 |
59
+ | 0.002 | 6.0 | 630 | 0.0165 | 22.8861 |
60
+ | 0.0018 | 7.0 | 735 | 0.0152 | 24.1263 |
61
+ | 0.0009 | 8.0 | 840 | 0.0161 | 24.5772 |
62
+ | 0.0006 | 9.0 | 945 | 0.0159 | 25.0282 |
63
+ | 0.0003 | 10.0 | 1050 | 0.0159 | 25.6483 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75229eddbdd7712110e325099bd2d8fa1f337554a4508f95d40f5461c6baa48c
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb49a85a6d63c0064a07a5a3b7436200a3715478ef2bde88278f6129a27c9c01
3
  size 151061672
runs/Jan24_11-05-32_b519fedc9610/events.out.tfevents.1706094334.b519fedc9610.15384.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:095149bd61fd6c8263b66cc5e1510d080d3942b35ce0a5ff56f818e36281916e
3
- size 15020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898e6dfa9898d7c40808105630e33b5880b8bd73f25d588a91a39d76d3ea4c55
3
+ size 15374