Agneev commited on
Commit
402d423
1 Parent(s): 1a36fd6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - PolyAI/minds14
9
+ metrics:
10
+ - wer
11
+ model-index:
12
+ - name: Whisper Tiny EN-US - Agneev M
13
+ results:
14
+ - task:
15
+ name: Automatic Speech Recognition
16
+ type: automatic-speech-recognition
17
+ dataset:
18
+ name: Minds 14
19
+ type: PolyAI/minds14
20
+ config: en-US
21
+ split: train
22
+ args: en-US
23
+ metrics:
24
+ - name: Wer
25
+ type: wer
26
+ value: 0.3488372093023256
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # Whisper Tiny EN-US - Agneev M
33
+
34
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Minds 14 dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.6326
37
+ - Wer Ortho: 0.3668
38
+ - Wer: 0.3488
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 1e-05
58
+ - train_batch_size: 64
59
+ - eval_batch_size: 64
60
+ - seed: 42
61
+ - gradient_accumulation_steps: 2
62
+ - total_train_batch_size: 128
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: constant_with_warmup
65
+ - lr_scheduler_warmup_steps: 5
66
+ - training_steps: 50
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
71
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
72
+ | 0.3661 | 14.29 | 50 | 0.6326 | 0.3668 | 0.3488 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.30.2
78
+ - Pytorch 2.0.0
79
+ - Datasets 2.1.0
80
+ - Tokenizers 0.13.3