Hugging Face's logo

sumet
/
whisper-tiny-en-US

Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
sumet commited on
Commit
f2f8ea0
•
1 Parent(s): 0a75bda

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +116 -0
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-tiny
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - PolyAI/minds14
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: whisper-tiny-en-US
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: PolyAI/minds14
18
+ type: PolyAI/minds14
19
+ config: en-AU
20
+ split: train
21
+ args: en-AU
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.1655499720826354
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # whisper-tiny-en-US
32
+
33
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.4245
36
+ - Wer Ortho: 0.1714
37
+ - Wer: 0.1655
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 1e-05
57
+ - train_batch_size: 16
58
+ - eval_batch_size: 16
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: constant_with_warmup
62
+ - lr_scheduler_warmup_steps: 5
63
+ - training_steps: 400
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
69
+ | No log | 0.36 | 10 | 3.1022 | 0.3282 | 0.1960 |
70
+ | No log | 0.71 | 20 | 1.6867 | 0.2399 | 0.1865 |
71
+ | 2.9245 | 1.07 | 30 | 0.6685 | 0.2332 | 0.1982 |
72
+ | 2.9245 | 1.43 | 40 | 0.4912 | 0.2017 | 0.1848 |
73
+ | 0.6297 | 1.79 | 50 | 0.4243 | 0.1865 | 0.1753 |
74
+ | 0.6297 | 2.14 | 60 | 0.3895 | 0.1801 | 0.1689 |
75
+ | 0.6297 | 2.5 | 70 | 0.3678 | 0.1769 | 0.1669 |
76
+ | 0.3045 | 2.86 | 80 | 0.3570 | 0.1746 | 0.1689 |
77
+ | 0.3045 | 3.21 | 90 | 0.3496 | 0.1720 | 0.1647 |
78
+ | 0.1949 | 3.57 | 100 | 0.3451 | 0.1746 | 0.1661 |
79
+ | 0.1949 | 3.93 | 110 | 0.3407 | 0.1804 | 0.1700 |
80
+ | 0.1949 | 4.29 | 120 | 0.3439 | 0.1778 | 0.1695 |
81
+ | 0.1099 | 4.64 | 130 | 0.3501 | 0.1743 | 0.1689 |
82
+ | 0.1099 | 5.0 | 140 | 0.3488 | 0.1737 | 0.1667 |
83
+ | 0.0583 | 5.36 | 150 | 0.3554 | 0.1778 | 0.1697 |
84
+ | 0.0583 | 5.71 | 160 | 0.3595 | 0.1708 | 0.1628 |
85
+ | 0.0583 | 6.07 | 170 | 0.3514 | 0.1746 | 0.1661 |
86
+ | 0.032 | 6.43 | 180 | 0.3672 | 0.1755 | 0.1683 |
87
+ | 0.032 | 6.79 | 190 | 0.3676 | 0.1676 | 0.1602 |
88
+ | 0.0146 | 7.14 | 200 | 0.3791 | 0.1658 | 0.1600 |
89
+ | 0.0146 | 7.5 | 210 | 0.3825 | 0.1676 | 0.1625 |
90
+ | 0.0146 | 7.86 | 220 | 0.3799 | 0.1702 | 0.1650 |
91
+ | 0.0084 | 8.21 | 230 | 0.3827 | 0.1702 | 0.1655 |
92
+ | 0.0084 | 8.57 | 240 | 0.3869 | 0.1778 | 0.1714 |
93
+ | 0.0043 | 8.93 | 250 | 0.3951 | 0.1740 | 0.1686 |
94
+ | 0.0043 | 9.29 | 260 | 0.3958 | 0.1720 | 0.1672 |
95
+ | 0.0043 | 9.64 | 270 | 0.3968 | 0.1758 | 0.1706 |
96
+ | 0.003 | 10.0 | 280 | 0.3978 | 0.1725 | 0.1672 |
97
+ | 0.003 | 10.36 | 290 | 0.4012 | 0.1734 | 0.1681 |
98
+ | 0.0023 | 10.71 | 300 | 0.4068 | 0.1728 | 0.1678 |
99
+ | 0.0023 | 11.07 | 310 | 0.4097 | 0.1752 | 0.1697 |
100
+ | 0.0023 | 11.43 | 320 | 0.4113 | 0.1746 | 0.1692 |
101
+ | 0.0018 | 11.79 | 330 | 0.4120 | 0.1737 | 0.1681 |
102
+ | 0.0018 | 12.14 | 340 | 0.4141 | 0.1740 | 0.1683 |
103
+ | 0.0016 | 12.5 | 350 | 0.4172 | 0.1731 | 0.1678 |
104
+ | 0.0016 | 12.86 | 360 | 0.4193 | 0.1740 | 0.1681 |
105
+ | 0.0016 | 13.21 | 370 | 0.4197 | 0.1731 | 0.1672 |
106
+ | 0.0014 | 13.57 | 380 | 0.4215 | 0.1731 | 0.1672 |
107
+ | 0.0014 | 13.93 | 390 | 0.4228 | 0.1720 | 0.1664 |
108
+ | 0.0012 | 14.29 | 400 | 0.4245 | 0.1714 | 0.1655 |
109
+
110
+
111
+ ### Framework versions
112
+
113
+ - Transformers 4.31.0.dev0
114
+ - Pytorch 2.0.1+cu118
115
+ - Datasets 2.13.1
116
+ - Tokenizers 0.13.3