Hugging Face's logo

denden
/
iloko_model

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
denden commited on
Commit
61cec28
•
1 Parent(s): 5706cf1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -18
README.md CHANGED
@@ -2,12 +2,6 @@
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
- - audio
6
- - automatic-speech-recognition
7
- - speech # Example: speech
8
-
9
- pipeline_tag: automatic-speech-recognition
10
-
11
  model-index:
12
  name: iloko_model
13
  ---
@@ -19,8 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0663
23
- - Wer: 0.1235
24
 
25
  ## Model description
26
 
@@ -48,21 +42,39 @@ The following hyperparameters were used during training:
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 500
51
- - num_epochs: 10
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|
57
- | 3.4454 | 1.11 | 100 | 3.0569 | 1.0 |
58
- | 2.6883 | 2.22 | 200 | 2.6725 | 1.0 |
59
- | 2.6082 | 3.33 | 300 | 2.6133 | 1.0 |
60
- | 1.7907 | 4.44 | 400 | 1.4020 | 0.9996 |
61
- | 0.5616 | 5.56 | 500 | 0.2521 | 0.3217 |
62
- | 0.2554 | 6.67 | 600 | 0.1373 | 0.1981 |
63
- | 0.1604 | 7.78 | 700 | 0.0904 | 0.1468 |
64
- | 0.1507 | 8.89 | 800 | 0.0740 | 0.1308 |
65
- | 0.1012 | 10.0 | 900 | 0.0663 | 0.1235 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
 
 
 
 
 
 
5
  model-index:
6
  name: iloko_model
7
  ---
 
13
 
14
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.0095
17
+ - Wer: 0.0840
18
 
19
  ## Model description
20
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 500
45
+ - num_epochs: 30
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Wer |
50
  |:-------------:|:-----:|:----:|:---------------:|:------:|
51
+ | 3.2784 | 1.11 | 100 | 2.9875 | 1.0 |
52
+ | 2.6899 | 2.22 | 200 | 2.6741 | 1.0 |
53
+ | 2.6177 | 3.33 | 300 | 2.6516 | 1.0 |
54
+ | 2.5327 | 4.44 | 400 | 2.4530 | 1.0 |
55
+ | 0.8653 | 5.56 | 500 | 0.5227 | 0.6547 |
56
+ | 0.3414 | 6.67 | 600 | 0.1830 | 0.2487 |
57
+ | 0.2299 | 7.78 | 700 | 0.1212 | 0.1877 |
58
+ | 0.1739 | 8.89 | 800 | 0.0843 | 0.1441 |
59
+ | 0.1242 | 10.0 | 900 | 0.0766 | 0.1441 |
60
+ | 0.1116 | 11.11 | 1000 | 0.0530 | 0.1145 |
61
+ | 0.0861 | 12.22 | 1100 | 0.0442 | 0.1047 |
62
+ | 0.1007 | 13.33 | 1200 | 0.0379 | 0.1023 |
63
+ | 0.0613 | 14.44 | 1300 | 0.0291 | 0.1006 |
64
+ | 0.0629 | 15.56 | 1400 | 0.0264 | 0.0961 |
65
+ | 0.047 | 16.67 | 1500 | 0.0238 | 0.0935 |
66
+ | 0.0797 | 17.78 | 1600 | 0.0226 | 0.0913 |
67
+ | 0.034 | 18.89 | 1700 | 0.0197 | 0.0893 |
68
+ | 0.0485 | 20.0 | 1800 | 0.0173 | 0.0905 |
69
+ | 0.0402 | 21.11 | 1900 | 0.0148 | 0.0902 |
70
+ | 0.0231 | 22.22 | 2000 | 0.0135 | 0.0891 |
71
+ | 0.0512 | 23.33 | 2100 | 0.0134 | 0.0861 |
72
+ | 0.0181 | 24.44 | 2200 | 0.0118 | 0.0842 |
73
+ | 0.0371 | 25.56 | 2300 | 0.0116 | 0.0867 |
74
+ | 0.0342 | 26.67 | 2400 | 0.0104 | 0.0863 |
75
+ | 0.0344 | 27.78 | 2500 | 0.0100 | 0.0850 |
76
+ | 0.0182 | 28.89 | 2600 | 0.0096 | 0.0839 |
77
+ | 0.0171 | 30.0 | 2700 | 0.0095 | 0.0840 |
78
 
79
 
80
  ### Framework versions