ptah23 commited on
Commit
d81a0f9
1 Parent(s): 5744020

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.20146619603584034
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: 0.6756
36
+ - Wer Ortho: 0.2044
37
+ - Wer: 0.2015
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: 50
63
+ - training_steps: 4000
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|
69
+ | 0.0007 | 17.86 | 500 | 0.5138 | 0.1941 | 0.1920 |
70
+ | 0.0002 | 35.71 | 1000 | 0.5565 | 0.1958 | 0.1936 |
71
+ | 0.0001 | 53.57 | 1500 | 0.5851 | 0.1981 | 0.1958 |
72
+ | 0.0001 | 71.43 | 2000 | 0.6081 | 0.2030 | 0.1998 |
73
+ | 0.0 | 89.29 | 2500 | 0.6273 | 0.2038 | 0.2009 |
74
+ | 0.0 | 107.14 | 3000 | 0.6441 | 0.2021 | 0.1996 |
75
+ | 0.0 | 125.0 | 3500 | 0.6602 | 0.2035 | 0.2007 |
76
+ | 0.0 | 142.86 | 4000 | 0.6756 | 0.2044 | 0.2015 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.31.0.dev0
82
+ - Pytorch 1.12.1+cu116
83
+ - Datasets 2.4.0
84
+ - Tokenizers 0.12.1