lorenzoncina commited on
Commit
7e021ab
1 Parent(s): 46cc6b1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-small
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: en
19
+ split: test
20
+ args: en
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 12.141503068470264
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-small
31
+
32
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_11_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.3104
35
+ - Wer: 12.1415
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: 32
56
+ - eval_batch_size: 16
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_steps: 500
61
+ - training_steps: 40000
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|
68
+ | 0.1577 | 0.06 | 2500 | 0.4077 | 16.2349 |
69
+ | 0.2244 | 0.12 | 5000 | 0.3698 | 14.7325 |
70
+ | 0.3231 | 0.19 | 7500 | 0.3434 | 13.7448 |
71
+ | 0.2536 | 0.25 | 10000 | 0.3406 | 13.4981 |
72
+ | 0.2234 | 0.31 | 12500 | 0.3510 | 14.1304 |
73
+ | 0.1989 | 0.38 | 15000 | 0.3388 | 13.6394 |
74
+ | 0.2449 | 0.44 | 17500 | 0.3394 | 13.4293 |
75
+ | 0.2302 | 0.5 | 20000 | 0.3198 | 12.5020 |
76
+ | 0.213 | 0.56 | 22500 | 0.3167 | 12.4904 |
77
+ | 0.2395 | 0.62 | 25000 | 0.3145 | 12.7533 |
78
+ | 0.1152 | 0.69 | 27500 | 0.3181 | 12.6087 |
79
+ | 0.0901 | 1.01 | 30000 | 0.3134 | 12.3240 |
80
+ | 0.1595 | 1.07 | 32500 | 0.3107 | 12.0213 |
81
+ | 0.1249 | 1.13 | 35000 | 0.3131 | 12.0869 |
82
+ | 0.1404 | 1.2 | 37500 | 0.3117 | 12.4635 |
83
+ | 0.1812 | 1.26 | 40000 | 0.3104 | 12.1415 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.28.0.dev0
89
+ - Pytorch 2.0.0+cu117
90
+ - Datasets 2.11.1.dev0
91
+ - Tokenizers 0.13.2