Jens commited on
Commit
53e795a
1 Parent(s): f669fe8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - dv
4
+ license: apache-2.0
5
+ base_model: openai/whisper-small
6
+ tags:
7
+ - generated_from_trainer
8
+ datasets:
9
+ - mozilla-foundation/common_voice_13_0
10
+ metrics:
11
+ - wer
12
+ model-index:
13
+ - name: Whisper Small Dv - Sanchit Gandhi
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 13
20
+ type: mozilla-foundation/common_voice_13_0
21
+ config: dv
22
+ split: test
23
+ args: dv
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 11.631950481621868
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 Dv - 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 13 dataset.
36
+ It achieves the following results on the evaluation set:
37
+ - Loss: 0.3085
38
+ - Wer Ortho: 58.3606
39
+ - Wer: 11.6320
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: 16
61
+ - seed: 42
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: constant_with_warmup
64
+ - lr_scheduler_warmup_steps: 50
65
+ - training_steps: 4000
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
70
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
71
+ | 0.1119 | 1.63 | 500 | 0.1645 | 60.8817 | 12.9082 |
72
+ | 0.0457 | 3.26 | 1000 | 0.1677 | 59.3286 | 11.7450 |
73
+ | 0.0317 | 4.89 | 1500 | 0.1903 | 58.3258 | 11.3798 |
74
+ | 0.012 | 6.51 | 2000 | 0.2292 | 58.0403 | 11.7085 |
75
+ | 0.007 | 8.14 | 2500 | 0.2595 | 56.9538 | 11.0982 |
76
+ | 0.0061 | 9.77 | 3000 | 0.2606 | 56.6404 | 10.8878 |
77
+ | 0.0052 | 11.4 | 3500 | 0.2737 | 56.8911 | 11.1799 |
78
+ | 0.0033 | 13.03 | 4000 | 0.3085 | 58.3606 | 11.6320 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.32.0.dev0
84
+ - Pytorch 2.0.1+cu117
85
+ - Datasets 2.13.1
86
+ - Tokenizers 0.13.3