Hugging Face's logo

MariaK
/
whisper-tiny-minds-v1

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
1
MariaK commited on
Commit
cecef20
·
1 Parent(s): ece4b76

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +94 -0
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - PolyAI/minds14
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: whisper-tiny-minds-v1
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: minds14
17
+ type: PolyAI/minds14
18
+ config: null
19
+ split: None
20
+ metrics:
21
+ - name: Wer
22
+ type: wer
23
+ value: 0.38044126416219437
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # whisper-tiny-minds-v1
30
+
31
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the minds14 dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 0.7887
34
+ - Wer Ortho: 0.4046
35
+ - Wer: 0.3804
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
+ - 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: 2000
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
66
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
67
+ | 1.7167 | 3.57 | 100 | 1.3603 | 0.5324 | 0.4132 |
68
+ | 0.3753 | 7.14 | 200 | 0.5665 | 0.4695 | 0.3894 |
69
+ | 0.1274 | 10.71 | 300 | 0.5589 | 0.4626 | 0.3912 |
70
+ | 0.0207 | 14.29 | 400 | 0.6216 | 0.4327 | 0.3834 |
71
+ | 0.0045 | 17.86 | 500 | 0.6684 | 0.4121 | 0.3697 |
72
+ | 0.0017 | 21.43 | 600 | 0.7018 | 0.4171 | 0.3792 |
73
+ | 0.0009 | 25.0 | 700 | 0.7218 | 0.4239 | 0.3876 |
74
+ | 0.0007 | 28.57 | 800 | 0.7272 | 0.4102 | 0.3781 |
75
+ | 0.0005 | 32.14 | 900 | 0.7427 | 0.4077 | 0.3787 |
76
+ | 0.0004 | 35.71 | 1000 | 0.7512 | 0.4077 | 0.3787 |
77
+ | 0.0004 | 39.29 | 1100 | 0.7573 | 0.4034 | 0.3757 |
78
+ | 0.0003 | 42.86 | 1200 | 0.7650 | 0.4027 | 0.3751 |
79
+ | 0.0003 | 46.43 | 1300 | 0.7714 | 0.4059 | 0.3769 |
80
+ | 0.0002 | 50.0 | 1400 | 0.7759 | 0.4052 | 0.3775 |
81
+ | 0.0002 | 53.57 | 1500 | 0.7796 | 0.4077 | 0.3798 |
82
+ | 0.0002 | 57.14 | 1600 | 0.7831 | 0.4046 | 0.3798 |
83
+ | 0.0002 | 60.71 | 1700 | 0.7858 | 0.4040 | 0.3792 |
84
+ | 0.0002 | 64.29 | 1800 | 0.7873 | 0.4040 | 0.3792 |
85
+ | 0.0002 | 67.86 | 1900 | 0.7883 | 0.4034 | 0.3792 |
86
+ | 0.0002 | 71.43 | 2000 | 0.7887 | 0.4046 | 0.3804 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.30.2
92
+ - Pytorch 2.0.1+cu118
93
+ - Datasets 2.13.1
94
+ - Tokenizers 0.13.3