nandovallec commited on
Commit
79596a3
1 Parent(s): 31b20ac

End of training

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - bg
4
+ license: apache-2.0
5
+ tags:
6
+ - hf-asr-leaderboard
7
+ - generated_from_trainer
8
+ datasets:
9
+ - mozilla-foundation/common_voice_11_0
10
+ metrics:
11
+ - wer
12
+ model-index:
13
+ - name: Whisper Small Bg - Yonchevisky_tes2t
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 11.0
20
+ type: mozilla-foundation/common_voice_11_0
21
+ config: bg
22
+ split: test
23
+ args: 'config: hi, split: test'
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 61.83524504692388
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 Small Bg - Yonchevisky_tes2t
34
+
35
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
36
+ It achieves the following results on the evaluation set:
37
+ - Loss: 0.7377
38
+ - Wer: 61.8352
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: 2
59
+ - eval_batch_size: 2
60
+ - seed: 42
61
+ - gradient_accumulation_steps: 8
62
+ - total_train_batch_size: 16
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: linear
65
+ - lr_scheduler_warmup_steps: 500
66
+ - training_steps: 1000
67
+ - mixed_precision_training: Native AMP
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
72
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
73
+ | 1.8067 | 0.37 | 100 | 1.6916 | 137.6897 |
74
+ | 0.9737 | 0.73 | 200 | 1.1197 | 78.3571 |
75
+ | 0.7747 | 1.1 | 300 | 0.9763 | 73.8906 |
76
+ | 0.6672 | 1.47 | 400 | 0.8972 | 70.7102 |
77
+ | 0.6196 | 1.84 | 500 | 0.8329 | 67.4545 |
78
+ | 0.4849 | 2.21 | 600 | 0.7968 | 66.6029 |
79
+ | 0.4402 | 2.57 | 700 | 0.7597 | 62.7795 |
80
+ | 0.4601 | 2.94 | 800 | 0.7385 | 61.8642 |
81
+ | 0.3545 | 3.31 | 900 | 0.7394 | 61.5050 |
82
+ | 0.3596 | 3.68 | 1000 | 0.7377 | 61.8352 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.26.0.dev0
88
+ - Pytorch 1.13.0+cu117
89
+ - Datasets 2.7.1
90
+ - Tokenizers 0.13.2