Hugging Face's logo

Jingmiao
/
whisper-small-chinese_base

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
Jingmiao commited on
Commit
43d3f65
•
1 Parent(s): 6268be8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -15
README.md CHANGED
@@ -1,39 +1,38 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - whisper-event
5
  - generated_from_trainer
6
  datasets:
7
- - google/fleurs
8
  metrics:
9
  - wer
10
  model-index:
11
- - name: Whisper Small Chinese Base
12
  results:
13
  - task:
14
  name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
16
  dataset:
17
- name: google/fleurs cmn_hans_cn
18
- type: google/fleurs
19
  config: cmn_hans_cn
20
  split: test
21
  args: cmn_hans_cn
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 16.643891773708663
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
- # Whisper Small Chinese Base
32
 
33
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs cmn_hans_cn dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3573
36
- - Wer: 16.6439
37
 
38
  ## Model description
39
 
@@ -66,11 +65,11 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer |
68
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
69
- | 0.0005 | 76.0 | 1000 | 0.3573 | 16.6439 |
70
- | 0.0002 | 153.0 | 2000 | 0.3897 | 16.9749 |
71
- | 0.0001 | 230.0 | 3000 | 0.4125 | 17.2330 |
72
- | 0.0001 | 307.0 | 4000 | 0.4256 | 17.2451 |
73
- | 0.0001 | 384.0 | 5000 | 0.4330 | 17.2300 |
74
 
75
 
76
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
  tags:
 
4
  - generated_from_trainer
5
  datasets:
6
+ - fleurs
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: openai/whisper-small
11
  results:
12
  - task:
13
  name: Automatic Speech Recognition
14
  type: automatic-speech-recognition
15
  dataset:
16
+ name: fleurs
17
+ type: fleurs
18
  config: cmn_hans_cn
19
  split: test
20
  args: cmn_hans_cn
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 16.05478120919498
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
  should probably proofread and complete it, then remove this comment. -->
29
 
30
+ # openai/whisper-small
31
 
32
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the fleurs dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.3537
35
+ - Wer: 16.0548
36
 
37
  ## Model description
38
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
68
+ | 0.0013 | 19.01 | 1000 | 0.2910 | 14.9282 |
69
+ | 0.0005 | 39.0 | 2000 | 0.3185 | 15.6327 |
70
+ | 0.0002 | 58.01 | 3000 | 0.3369 | 15.6965 |
71
+ | 0.0002 | 78.0 | 4000 | 0.3480 | 16.0669 |
72
+ | 0.0001 | 98.0 | 5000 | 0.3537 | 16.0548 |
73
 
74
 
75
  ### Framework versions