noflm commited on
Commit
81dd039
1 Parent(s): 90e6d3e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - elite_voice_project
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: whisper-small-ja-elite
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: elite_voice_project
17
+ type: elite_voice_project
18
+ config: twitter
19
+ split: test
20
+ args: twitter
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 4.878048780487805
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
+ # whisper-small-ja-elite
31
+
32
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the elite_voice_project dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.1502
35
+ - Wer: 4.8780
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 1e-05
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: constant_with_warmup
60
+ - lr_scheduler_warmup_steps: 50
61
+ - training_steps: 5000
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
68
+ | 0.0004 | 58.0 | 1000 | 0.1129 | 1.8293 |
69
+ | 0.0 | 117.0 | 2000 | 0.1232 | 1.8293 |
70
+ | 0.0 | 176.0 | 3000 | 0.1327 | 1.8293 |
71
+ | 0.0 | 235.0 | 4000 | 0.1401 | 4.8780 |
72
+ | 0.0 | 294.0 | 5000 | 0.1502 | 4.8780 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.26.0.dev0
78
+ - Pytorch 1.13.1+cu117
79
+ - Datasets 2.8.1.dev0
80
+ - Tokenizers 0.13.2