tuananh7198 commited on
Commit
4af3796
1 Parent(s): 7573c3f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -4
README.md CHANGED
@@ -4,9 +4,24 @@ tags:
4
  - generated_from_trainer
5
  datasets:
6
  - common_voice_11_0
 
 
7
  model-index:
8
  - name: openai/whisper-medium
9
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,6 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
15
  # openai/whisper-medium
16
 
17
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the common_voice_11_0 dataset.
 
 
 
18
 
19
  ## Model description
20
 
@@ -34,17 +52,20 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 1e-05
37
- - train_batch_size: 32
38
- - eval_batch_size: 64
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - lr_scheduler_warmup_steps: 100
43
- - training_steps: 1
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
 
 
 
48
 
49
 
50
  ### Framework versions
 
4
  - generated_from_trainer
5
  datasets:
6
  - common_voice_11_0
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: openai/whisper-medium
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_11_0
17
+ type: common_voice_11_0
18
+ config: vi
19
+ split: test
20
+ args: vi
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 20.04825619653433
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
  # openai/whisper-medium
31
 
32
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the common_voice_11_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.5422
35
+ - Wer: 20.0483
36
 
37
  ## Model description
38
 
 
52
 
53
  The following hyperparameters were used during training:
54
  - learning_rate: 1e-05
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 16
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
  - lr_scheduler_warmup_steps: 100
61
+ - training_steps: 1000
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
68
+ | 0.0241 | 4.01 | 1000 | 0.5422 | 20.0483 |
69
 
70
 
71
  ### Framework versions