seyidov579 commited on
Commit
3b7dc41
1 Parent(s): df78643

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - az
4
+ license: apache-2.0
5
+ tags:
6
+ - hf-asr-leaderboard
7
+ - generated_from_trainer
8
+ datasets:
9
+ - seyidov579/azerbaijan
10
+ metrics:
11
+ - wer
12
+ model-index:
13
+ - name: Whisper Tiny Az - Kenan Seyidov
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 13.0
20
+ type: seyidov579/azerbaijan
21
+ config: az_az
22
+ split: test
23
+ args: 'config: az, split: test'
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 100.0
28
+ ---
29
+
30
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
+ should probably proofread and complete it, then remove this comment. -->
32
+
33
+ # Whisper Tiny Az - Kenan Seyidov
34
+
35
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 13.0 dataset.
36
+ It achieves the following results on the evaluation set:
37
+ - Loss: 2.5260
38
+ - Wer: 100.0
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: 16
59
+ - eval_batch_size: 8
60
+ - seed: 42
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 500
64
+ - training_steps: 4000
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:------:|:----:|:---------------:|:-----:|
70
+ | 0.0 | 1000.0 | 1000 | 2.3577 | 100.0 |
71
+ | 0.0 | 2000.0 | 2000 | 2.4623 | 100.0 |
72
+ | 0.0 | 3000.0 | 3000 | 2.5096 | 100.0 |
73
+ | 0.0 | 4000.0 | 4000 | 2.5260 | 100.0 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.28.0
79
+ - Pytorch 2.0.1+cu118
80
+ - Datasets 2.12.0
81
+ - Tokenizers 0.13.3