Hugging Face's logo

jjyaoao
/
Echotune_clean_test

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
data2vec-audio
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
jjyaoao commited on
Commit
ac2885d
•
1 Parent(s): 4f983fd

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +133 -0
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/data2vec-audio-base-960h
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - librispeech_asr
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: jjyaoao/Echotune_clean_test
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: librispeech_asr
18
+ type: librispeech_asr
19
+ config: clean
20
+ split: test
21
+ args: clean
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.037368222891566265
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # jjyaoao/Echotune_clean_test
32
+
33
+ This model is a fine-tuned version of [facebook/data2vec-audio-base-960h](https://huggingface.co/facebook/data2vec-audio-base-960h) on the librispeech_asr dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.0679
36
+ - Wer Ortho: 0.0369
37
+ - Wer: 0.0374
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 6e-05
57
+ - train_batch_size: 12
58
+ - eval_batch_size: 12
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_steps: 34246.8
63
+ - num_epochs: 12
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|
69
+ | 0.0602 | 0.21 | 500 | 0.0476 | 0.0435 | 0.0439 |
70
+ | 0.0478 | 0.42 | 1000 | 0.0436 | 0.0411 | 0.0414 |
71
+ | 0.0492 | 0.63 | 1500 | 0.0443 | 0.0412 | 0.0415 |
72
+ | 0.0426 | 0.84 | 2000 | 0.0439 | 0.0401 | 0.0403 |
73
+ | 0.0386 | 1.05 | 2500 | 0.0445 | 0.0391 | 0.0395 |
74
+ | 0.0409 | 1.26 | 3000 | 0.0438 | 0.0394 | 0.0399 |
75
+ | 0.0437 | 1.47 | 3500 | 0.0444 | 0.0389 | 0.0393 |
76
+ | 0.0349 | 1.68 | 4000 | 0.0450 | 0.0392 | 0.0396 |
77
+ | 0.0469 | 1.89 | 4500 | 0.0442 | 0.0374 | 0.0378 |
78
+ | 0.033 | 2.1 | 5000 | 0.0454 | 0.0359 | 0.0363 |
79
+ | 0.0395 | 2.31 | 5500 | 0.0462 | 0.0363 | 0.0367 |
80
+ | 0.0321 | 2.52 | 6000 | 0.0457 | 0.0365 | 0.0369 |
81
+ | 0.0385 | 2.73 | 6500 | 0.0455 | 0.0355 | 0.0358 |
82
+ | 0.0378 | 2.94 | 7000 | 0.0449 | 0.0361 | 0.0366 |
83
+ | 0.0435 | 3.15 | 7500 | 0.0440 | 0.0355 | 0.0360 |
84
+ | 0.0436 | 3.36 | 8000 | 0.0466 | 0.0339 | 0.0344 |
85
+ | 0.0394 | 3.57 | 8500 | 0.0480 | 0.0345 | 0.0350 |
86
+ | 0.0448 | 3.78 | 9000 | 0.0478 | 0.0338 | 0.0342 |
87
+ | 0.0451 | 3.99 | 9500 | 0.0460 | 0.0355 | 0.0361 |
88
+ | 0.035 | 4.2 | 10000 | 0.0485 | 0.0369 | 0.0374 |
89
+ | 0.0387 | 4.41 | 10500 | 0.0487 | 0.0358 | 0.0362 |
90
+ | 0.0479 | 4.62 | 11000 | 0.0496 | 0.0363 | 0.0368 |
91
+ | 0.0456 | 4.83 | 11500 | 0.0491 | 0.0359 | 0.0365 |
92
+ | 0.0372 | 5.04 | 12000 | 0.0507 | 0.0355 | 0.0360 |
93
+ | 0.0395 | 5.25 | 12500 | 0.0526 | 0.0353 | 0.0356 |
94
+ | 0.0323 | 5.46 | 13000 | 0.0515 | 0.0368 | 0.0373 |
95
+ | 0.0354 | 5.67 | 13500 | 0.0524 | 0.0338 | 0.0343 |
96
+ | 0.031 | 5.88 | 14000 | 0.0531 | 0.0349 | 0.0357 |
97
+ | 0.0295 | 6.09 | 14500 | 0.0560 | 0.0344 | 0.0349 |
98
+ | 0.032 | 6.31 | 15000 | 0.0564 | 0.0364 | 0.0369 |
99
+ | 0.0462 | 6.52 | 15500 | 0.0548 | 0.0358 | 0.0365 |
100
+ | 0.0467 | 6.73 | 16000 | 0.0562 | 0.0347 | 0.0352 |
101
+ | 0.0437 | 6.94 | 16500 | 0.0573 | 0.0354 | 0.0359 |
102
+ | 0.0357 | 7.15 | 17000 | 0.0561 | 0.0359 | 0.0362 |
103
+ | 0.0297 | 7.36 | 17500 | 0.0602 | 0.0347 | 0.0351 |
104
+ | 0.0388 | 7.57 | 18000 | 0.0552 | 0.0341 | 0.0345 |
105
+ | 0.0392 | 7.78 | 18500 | 0.0533 | 0.0326 | 0.0331 |
106
+ | 0.0419 | 7.99 | 19000 | 0.0535 | 0.0343 | 0.0349 |
107
+ | 0.0326 | 8.2 | 19500 | 0.0614 | 0.0374 | 0.0378 |
108
+ | 0.0423 | 8.41 | 20000 | 0.0585 | 0.0341 | 0.0346 |
109
+ | 0.0326 | 8.62 | 20500 | 0.0586 | 0.0356 | 0.0362 |
110
+ | 0.0448 | 8.83 | 21000 | 0.0637 | 0.0371 | 0.0375 |
111
+ | 0.0763 | 9.04 | 21500 | 0.0607 | 0.0359 | 0.0364 |
112
+ | 0.0317 | 9.25 | 22000 | 0.0635 | 0.0400 | 0.0405 |
113
+ | 0.0326 | 9.46 | 22500 | 0.0603 | 0.0368 | 0.0372 |
114
+ | 0.0393 | 9.67 | 23000 | 0.0665 | 0.0380 | 0.0385 |
115
+ | 0.0341 | 9.88 | 23500 | 0.0664 | 0.0408 | 0.0413 |
116
+ | 0.0351 | 10.09 | 24000 | 0.0638 | 0.0384 | 0.0388 |
117
+ | 0.0412 | 10.3 | 24500 | 0.0687 | 0.0380 | 0.0384 |
118
+ | 0.0359 | 10.51 | 25000 | 0.0634 | 0.0379 | 0.0385 |
119
+ | 0.047 | 10.72 | 25500 | 0.0652 | 0.0373 | 0.0378 |
120
+ | 0.0346 | 10.93 | 26000 | 0.0671 | 0.0390 | 0.0396 |
121
+ | 0.0366 | 11.14 | 26500 | 0.0664 | 0.0387 | 0.0393 |
122
+ | 0.0359 | 11.35 | 27000 | 0.0669 | 0.0369 | 0.0374 |
123
+ | 0.0366 | 11.56 | 27500 | 0.0705 | 0.0358 | 0.0364 |
124
+ | 0.054 | 11.77 | 28000 | 0.0659 | 0.0383 | 0.0390 |
125
+ | 0.0335 | 11.98 | 28500 | 0.0679 | 0.0369 | 0.0374 |
126
+
127
+
128
+ ### Framework versions
129
+
130
+ - Transformers 4.32.0.dev0
131
+ - Pytorch 2.0.0+cu117
132
+ - Datasets 2.13.1
133
+ - Tokenizers 0.13.3