Hugging Face's logo

Bajiyo
/
w2v-bert-2_7_datasets

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
Bajiyo commited on
Commit
8851323
·
verified ·
1 Parent(s): cfe0f40

End of training

Browse files
Files changed (1) hide show
  1. README.md +33 -46
README.md CHANGED
@@ -1,29 +1,14 @@
1
  ---
2
- base_model: facebook/w2v-bert-2.0
3
- datasets:
4
- - common_voice_17_0
5
  library_name: transformers
6
  license: mit
7
- metrics:
8
- - wer
9
  tags:
10
  - generated_from_trainer
 
 
11
  model-index:
12
  - name: w2v-bert-2_6_datasets
13
- results:
14
- - task:
15
- type: automatic-speech-recognition
16
- name: Automatic Speech Recognition
17
- dataset:
18
- name: common_voice_17_0
19
- type: common_voice_17_0
20
- config: ml
21
- split: validation
22
- args: ml
23
- metrics:
24
- - type: wer
25
- value: 0.43922053819981444
26
- name: Wer
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # w2v-bert-2_6_datasets
33
 
34
- This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the common_voice_17_0 dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.5077
37
- - Wer: 0.4392
38
 
39
  ## Model description
40
 
@@ -69,30 +54,32 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:------:|:-----:|:---------------:|:------:|
72
- | 1.1114 | 0.4038 | 600 | 0.6364 | 0.6514 |
73
- | 0.1782 | 0.8075 | 1200 | 0.5620 | 0.6127 |
74
- | 0.1374 | 1.2113 | 1800 | 0.4943 | 0.5654 |
75
- | 0.1156 | 1.6151 | 2400 | 0.4415 | 0.5376 |
76
- | 0.1068 | 2.0188 | 3000 | 0.4187 | 0.5249 |
77
- | 0.0838 | 2.4226 | 3600 | 0.4778 | 0.5320 |
78
- | 0.0834 | 2.8264 | 4200 | 0.4186 | 0.5091 |
79
- | 0.0703 | 3.2301 | 4800 | 0.4538 | 0.5363 |
80
- | 0.0636 | 3.6339 | 5400 | 0.4287 | 0.5314 |
81
- | 0.0609 | 4.0377 | 6000 | 0.4013 | 0.4989 |
82
- | 0.0462 | 4.4415 | 6600 | 0.4053 | 0.4964 |
83
- | 0.047 | 4.8452 | 7200 | 0.4289 | 0.4766 |
84
- | 0.0377 | 5.2490 | 7800 | 0.3875 | 0.4933 |
85
- | 0.0352 | 5.6528 | 8400 | 0.3906 | 0.4881 |
86
- | 0.033 | 6.0565 | 9000 | 0.4192 | 0.4667 |
87
- | 0.0243 | 6.4603 | 9600 | 0.4113 | 0.4723 |
88
- | 0.0244 | 6.8641 | 10200 | 0.4393 | 0.4708 |
89
- | 0.0189 | 7.2678 | 10800 | 0.4255 | 0.4630 |
90
- | 0.0167 | 7.6716 | 11400 | 0.4219 | 0.4646 |
91
- | 0.0157 | 8.0754 | 12000 | 0.4398 | 0.4429 |
92
- | 0.0107 | 8.4791 | 12600 | 0.4546 | 0.4507 |
93
- | 0.0095 | 8.8829 | 13200 | 0.4949 | 0.4426 |
94
- | 0.0072 | 9.2867 | 13800 | 0.4972 | 0.4473 |
95
- | 0.0059 | 9.6904 | 14400 | 0.5077 | 0.4392 |
 
 
96
 
97
 
98
  ### Framework versions
 
1
  ---
 
 
 
2
  library_name: transformers
3
  license: mit
4
+ base_model: facebook/w2v-bert-2.0
 
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: w2v-bert-2_6_datasets
11
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
16
 
17
  # w2v-bert-2_6_datasets
18
 
19
+ This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3804
22
+ - Wer: 0.2629
23
 
24
  ## Model description
25
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:------:|:-----:|:---------------:|:------:|
57
+ | 1.1149 | 0.3795 | 600 | 0.5531 | 0.4947 |
58
+ | 0.2052 | 0.7590 | 1200 | 0.4347 | 0.4689 |
59
+ | 0.1576 | 1.1385 | 1800 | 0.3204 | 0.3717 |
60
+ | 0.1263 | 1.5180 | 2400 | 0.3928 | 0.4128 |
61
+ | 0.1205 | 1.8975 | 3000 | 0.3214 | 0.3607 |
62
+ | 0.0993 | 2.2770 | 3600 | 0.3063 | 0.3514 |
63
+ | 0.091 | 2.6565 | 4200 | 0.3078 | 0.3390 |
64
+ | 0.0877 | 3.0361 | 4800 | 0.2673 | 0.3165 |
65
+ | 0.0716 | 3.4156 | 5400 | 0.2798 | 0.3039 |
66
+ | 0.0681 | 3.7951 | 6000 | 0.2710 | 0.2948 |
67
+ | 0.0592 | 4.1746 | 6600 | 0.2728 | 0.3072 |
68
+ | 0.0525 | 4.5541 | 7200 | 0.2828 | 0.3133 |
69
+ | 0.0497 | 4.9336 | 7800 | 0.3039 | 0.3132 |
70
+ | 0.0402 | 5.3131 | 8400 | 0.2741 | 0.2832 |
71
+ | 0.0389 | 5.6926 | 9000 | 0.2837 | 0.3018 |
72
+ | 0.0371 | 6.0721 | 9600 | 0.2732 | 0.2830 |
73
+ | 0.0286 | 6.4516 | 10200 | 0.2998 | 0.2794 |
74
+ | 0.028 | 6.8311 | 10800 | 0.2904 | 0.2769 |
75
+ | 0.0232 | 7.2106 | 11400 | 0.3183 | 0.2752 |
76
+ | 0.0201 | 7.5901 | 12000 | 0.3045 | 0.2665 |
77
+ | 0.0197 | 7.9696 | 12600 | 0.3137 | 0.2733 |
78
+ | 0.0139 | 8.3491 | 13200 | 0.3438 | 0.2670 |
79
+ | 0.0128 | 8.7287 | 13800 | 0.3385 | 0.2651 |
80
+ | 0.0115 | 9.1082 | 14400 | 0.3669 | 0.2671 |
81
+ | 0.0079 | 9.4877 | 15000 | 0.3695 | 0.2613 |
82
+ | 0.008 | 9.8672 | 15600 | 0.3804 | 0.2629 |
83
 
84
 
85
  ### Framework versions