emon-j commited on
Commit
a7aa06a
1 Parent(s): 99272eb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +76 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-finetuned-tiny-v4
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: PolyAI/minds14
17
+ type: PolyAI/minds14
18
+ config: en-US
19
+ split: train
20
+ args: en-US
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.33884297520661155
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
+ # whisper-finetuned-tiny-v4
31
+
32
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.6512
35
+ - Wer Ortho: 34.2381
36
+ - Wer: 0.3388
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 1e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 16
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 20
62
+ - training_steps: 20
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
67
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
68
+ | 0.0452 | 1.33 | 20 | 0.6512 | 34.2381 | 0.3388 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.30.2
74
+ - Pytorch 1.13.1+cu117
75
+ - Datasets 2.13.2
76
+ - Tokenizers 0.13.3