duytran3112 commited on
Commit
a62836e
1 Parent(s): 3f4a8bb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - vi
4
+ license: apache-2.0
5
+ base_model: openai/whisper-small
6
+ tags:
7
+ - leaderboards
8
+ - generated_from_trainer
9
+ datasets:
10
+ - vivos
11
+ metrics:
12
+ - wer
13
+ model-index:
14
+ - name: Whisper - Vivos
15
+ results:
16
+ - task:
17
+ name: Automatic Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: Vivos
21
+ type: vivos
22
+ config: null
23
+ split: None
24
+ args: 'split: test'
25
+ metrics:
26
+ - name: Wer
27
+ type: wer
28
+ value: 54.85625485625486
29
+ ---
30
+
31
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
+ should probably proofread and complete it, then remove this comment. -->
33
+
34
+ # Whisper - Vivos
35
+
36
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Vivos dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.2370
39
+ - Wer: 54.8563
40
+
41
+ ## Model description
42
+
43
+ More information needed
44
+
45
+ ## Intended uses & limitations
46
+
47
+ More information needed
48
+
49
+ ## Training and evaluation data
50
+
51
+ More information needed
52
+
53
+ ## Training procedure
54
+
55
+ ### Training hyperparameters
56
+
57
+ The following hyperparameters were used during training:
58
+ - learning_rate: 1e-05
59
+ - train_batch_size: 16
60
+ - eval_batch_size: 8
61
+ - seed: 42
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 500
65
+ - training_steps: 4000
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
71
+ | 0.1265 | 1.37 | 1000 | 0.2178 | 35.8845 |
72
+ | 0.062 | 2.74 | 2000 | 0.2138 | 49.8446 |
73
+ | 0.0169 | 4.12 | 3000 | 0.2273 | 52.2922 |
74
+ | 0.012 | 5.49 | 4000 | 0.2370 | 54.8563 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.31.0
80
+ - Pytorch 2.0.0
81
+ - Datasets 2.13.1
82
+ - Tokenizers 0.13.3