Hugging Face's logo

BrilliantCoolHuge
/
whisper-tiny-hi

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Chinese
whisper
Generated from Trainer
Eval Results
Model card Files Metrics Community
1
BrilliantCoolHuge commited on
Commit
e3107db
·
1 Parent(s): f9214ad

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +100 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - hi
4
+ license: apache-2.0
5
+ tags:
6
+ - hf-asr-leaderboard
7
+ - generated_from_trainer
8
+ datasets:
9
+ - mozilla-foundation/common_voice_11_0
10
+ metrics:
11
+ - wer
12
+ model-index:
13
+ - name: Whisper Small Hi - Sanchit Gandhi
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 11.0
20
+ type: mozilla-foundation/common_voice_11_0
21
+ config: zh-CN
22
+ split: test[:1%]
23
+ args: 'config: hi, split: test'
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 226.41509433962264
28
+ ---
29
+
30
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
+ should probably proofread and complete it, then remove this comment. -->
32
+
33
+ # Whisper Small Hi - Sanchit Gandhi
34
+
35
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
36
+ It achieves the following results on the evaluation set:
37
+ - Loss: 1.7064
38
+ - Wer: 226.4151
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 1e-05
58
+ - train_batch_size: 8
59
+ - eval_batch_size: 8
60
+ - seed: 42
61
+ - gradient_accumulation_steps: 2
62
+ - total_train_batch_size: 16
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: linear
65
+ - lr_scheduler_warmup_steps: 5
66
+ - training_steps: 400
67
+ - mixed_precision_training: Native AMP
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
72
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
73
+ | 0.8417 | 1.08 | 20 | 1.4964 | 598.1132 |
74
+ | 1.2552 | 2.16 | 40 | 1.4901 | 367.9245 |
75
+ | 0.8195 | 3.24 | 60 | 1.4953 | 391.5094 |
76
+ | 0.6174 | 4.32 | 80 | 1.5091 | 475.4717 |
77
+ | 0.4594 | 5.41 | 100 | 1.5318 | 520.7547 |
78
+ | 0.489 | 6.49 | 120 | 1.5558 | 863.2075 |
79
+ | 0.4673 | 7.57 | 140 | 1.5719 | 663.2075 |
80
+ | 0.3976 | 8.65 | 160 | 1.5962 | 682.0755 |
81
+ | 0.3518 | 9.73 | 180 | 1.6160 | 623.5849 |
82
+ | 0.3043 | 10.81 | 200 | 1.6219 | 620.7547 |
83
+ | 0.2524 | 11.89 | 220 | 1.6505 | 598.1132 |
84
+ | 0.259 | 12.97 | 240 | 1.6543 | 329.2453 |
85
+ | 0.1696 | 14.05 | 260 | 1.6678 | 333.0189 |
86
+ | 0.1188 | 15.14 | 280 | 1.6746 | 329.2453 |
87
+ | 0.1366 | 16.22 | 300 | 1.6852 | 428.3019 |
88
+ | 0.1165 | 17.3 | 320 | 1.6979 | 262.2642 |
89
+ | 0.1062 | 18.38 | 340 | 1.7021 | 338.6792 |
90
+ | 0.0882 | 19.46 | 360 | 1.7047 | 313.2075 |
91
+ | 0.0891 | 20.54 | 380 | 1.7054 | 302.8302 |
92
+ | 0.0676 | 21.62 | 400 | 1.7064 | 226.4151 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.28.0.dev0
98
+ - Pytorch 1.11.0+cu102
99
+ - Datasets 2.10.1
100
+ - Tokenizers 0.13.2