jlondonobo commited on
Commit
1443405
1 Parent(s): c9fa76d

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
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_11_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: openai/whisper-large-v2
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: pt
19
+ split: test
20
+ args: pt
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 5.590020342630419
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
+ # openai/whisper-large-v2
31
+
32
+ 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.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.2821
35
+ - Wer: 5.5900
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
+ - gradient_accumulation_steps: 2
59
+ - total_train_batch_size: 32
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_steps: 500
63
+ - training_steps: 5000
64
+ - mixed_precision_training: Native AMP
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 0.0828 | 1.09 | 1000 | 0.1868 | 6.7786 |
71
+ | 0.0241 | 3.07 | 2000 | 0.2057 | 6.1095 |
72
+ | 0.0084 | 5.06 | 3000 | 0.2367 | 6.0288 |
73
+ | 0.0015 | 7.04 | 4000 | 0.2469 | 5.7094 |
74
+ | 0.0009 | 9.02 | 5000 | 0.2821 | 5.5900 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.26.0.dev0
80
+ - Pytorch 1.13.0+cu117
81
+ - Datasets 2.7.1.dev0
82
+ - Tokenizers 0.13.2