Hugging Face's logo

jangedoo
/
whisper-small-ne-NP

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
jangedoo commited on
Commit
cebe2f0
•
1 Parent(s): 7340dde

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +115 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_13_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: whisper-small-ne-NP
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_13_0
17
+ type: common_voice_13_0
18
+ config: ne-NP
19
+ split: test
20
+ args: ne-NP
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 57.38758029978587
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-small-ne-NP
31
+
32
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_13_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.6005
35
+ - Wer: 57.3876
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 1e-05
55
+ - train_batch_size: 4
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_steps: 500
61
+ - training_steps: 4000
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
68
+ | 0.9935 | 0.17 | 100 | 1.3460 | 91.4347 |
69
+ | 0.6624 | 0.35 | 200 | 1.0307 | 85.6531 |
70
+ | 0.5002 | 0.52 | 300 | 0.8406 | 77.5161 |
71
+ | 0.4426 | 0.7 | 400 | 0.7038 | 76.2313 |
72
+ | 0.3063 | 0.87 | 500 | 0.5308 | 71.5203 |
73
+ | 0.1949 | 1.05 | 600 | 0.5200 | 66.1670 |
74
+ | 0.1974 | 1.22 | 700 | 0.5140 | 65.0964 |
75
+ | 0.1734 | 1.4 | 800 | 0.4423 | 67.6660 |
76
+ | 0.1619 | 1.57 | 900 | 0.4705 | 62.0985 |
77
+ | 0.1697 | 1.75 | 1000 | 0.4676 | 67.0236 |
78
+ | 0.1536 | 1.92 | 1100 | 0.4441 | 62.7409 |
79
+ | 0.0722 | 2.1 | 1200 | 0.4492 | 58.0300 |
80
+ | 0.0674 | 2.27 | 1300 | 0.4597 | 59.9572 |
81
+ | 0.0766 | 2.45 | 1400 | 0.4720 | 62.3126 |
82
+ | 0.0732 | 2.62 | 1500 | 0.4720 | 60.5996 |
83
+ | 0.0737 | 2.8 | 1600 | 0.4704 | 61.0278 |
84
+ | 0.0833 | 2.97 | 1700 | 0.4711 | 59.7430 |
85
+ | 0.0421 | 3.15 | 1800 | 0.5040 | 60.5996 |
86
+ | 0.0444 | 3.32 | 1900 | 0.5096 | 62.5268 |
87
+ | 0.0343 | 3.5 | 2000 | 0.5276 | 62.5268 |
88
+ | 0.0347 | 3.67 | 2100 | 0.5068 | 57.3876 |
89
+ | 0.0326 | 3.85 | 2200 | 0.5143 | 59.3148 |
90
+ | 0.0219 | 4.02 | 2300 | 0.5225 | 59.3148 |
91
+ | 0.0129 | 4.2 | 2400 | 0.5353 | 59.1006 |
92
+ | 0.0159 | 4.37 | 2500 | 0.5639 | 56.9593 |
93
+ | 0.0168 | 4.55 | 2600 | 0.5303 | 55.8887 |
94
+ | 0.0131 | 4.72 | 2700 | 0.5455 | 58.6724 |
95
+ | 0.0122 | 4.9 | 2800 | 0.5548 | 56.5310 |
96
+ | 0.0035 | 5.07 | 2900 | 0.5661 | 56.7452 |
97
+ | 0.0027 | 5.24 | 3000 | 0.5789 | 57.6017 |
98
+ | 0.0034 | 5.42 | 3100 | 0.5887 | 59.1006 |
99
+ | 0.0047 | 5.59 | 3200 | 0.5853 | 59.9572 |
100
+ | 0.0054 | 5.77 | 3300 | 0.5912 | 58.4582 |
101
+ | 0.0042 | 5.94 | 3400 | 0.5862 | 59.3148 |
102
+ | 0.0013 | 6.12 | 3500 | 0.5935 | 56.7452 |
103
+ | 0.001 | 6.29 | 3600 | 0.5991 | 57.3876 |
104
+ | 0.0008 | 6.47 | 3700 | 0.6012 | 57.6017 |
105
+ | 0.0014 | 6.64 | 3800 | 0.6002 | 57.8158 |
106
+ | 0.001 | 6.82 | 3900 | 0.6006 | 57.8158 |
107
+ | 0.0013 | 6.99 | 4000 | 0.6005 | 57.3876 |
108
+
109
+
110
+ ### Framework versions
111
+
112
+ - Transformers 4.28.1
113
+ - Pytorch 2.0.0
114
+ - Datasets 2.11.0
115
+ - Tokenizers 0.13.3