simonl0909 commited on
Commit
eb41cc9
1 Parent(s): 7435bfe

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_11_0
7
+ model-index:
8
+ - name: models
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # models
16
+
17
+ This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_11_0 dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2957
20
+ - Cer: 6.7638
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 8
44
+ - total_train_batch_size: 64
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - training_steps: 5000
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 0.0032 | 13.01 | 1000 | 0.2318 | 6.8569 |
56
+ | 0.002 | 26.01 | 2000 | 0.2404 | 7.1524 |
57
+ | 0.0001 | 39.02 | 3000 | 0.2807 | 6.7274 |
58
+ | 0.0001 | 53.01 | 4000 | 0.2912 | 6.7517 |
59
+ | 0.0 | 66.01 | 5000 | 0.2957 | 6.7638 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.26.0.dev0
65
+ - Pytorch 1.13.0+cu117
66
+ - Datasets 2.7.1.dev0
67
+ - Tokenizers 0.13.2