Hugging Face's logo

tz579
/
wav2vec2-base-timit-fine-tuned

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
timit_asr
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
tz579 commited on
Commit
3f69173
•
1 Parent(s): 6c3ffe4

Model save

Browse files
Files changed (1) hide show
  1. README.md +30 -33
README.md CHANGED
@@ -1,9 +1,6 @@
1
  ---
2
- license: apache-2.0
3
  base_model: facebook/wav2vec2-base
4
  tags:
5
- - automatic-speech-recognition
6
- - timit_asr
7
  - generated_from_trainer
8
  datasets:
9
  - timit_asr
@@ -16,15 +13,15 @@ model-index:
16
  name: Automatic Speech Recognition
17
  type: automatic-speech-recognition
18
  dataset:
19
- name: TIMIT_ASR - NA
20
  type: timit_asr
21
  config: clean
22
  split: test
23
- args: 'Config: na, Training split: train, Eval split: test'
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 0.41728125284530637
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  # wav2vec2-base-timit-fine-tuned
34
 
35
- This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the TIMIT_ASR - NA dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.4275
38
- - Wer: 0.4173
39
 
40
  ## Model description
41
 
@@ -68,34 +65,34 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:-------:|:----:|:---------------:|:------:|
71
- | 3.1618 | 0.8621 | 100 | 3.1117 | 1.0 |
72
- | 2.9798 | 1.7241 | 200 | 2.9736 | 1.0 |
73
- | 2.9144 | 2.5862 | 300 | 2.9075 | 1.0 |
74
- | 2.1714 | 3.4483 | 400 | 2.0945 | 1.0325 |
75
- | 1.1579 | 4.3103 | 500 | 1.0451 | 0.8299 |
76
- | 0.6087 | 5.1724 | 600 | 0.6754 | 0.6441 |
77
- | 0.481 | 6.0345 | 700 | 0.5275 | 0.5761 |
78
- | 0.3072 | 6.8966 | 800 | 0.4836 | 0.5264 |
79
- | 0.332 | 7.7586 | 900 | 0.4403 | 0.5234 |
80
- | 0.1876 | 8.6207 | 1000 | 0.4758 | 0.5222 |
81
- | 0.2232 | 9.4828 | 1100 | 0.4508 | 0.4892 |
82
- | 0.1332 | 10.3448 | 1200 | 0.4394 | 0.4740 |
83
- | 0.1085 | 11.2069 | 1300 | 0.4466 | 0.4621 |
84
- | 0.098 | 12.0690 | 1400 | 0.4230 | 0.4493 |
85
- | 0.1219 | 12.9310 | 1500 | 0.4180 | 0.4460 |
86
- | 0.1021 | 13.7931 | 1600 | 0.4179 | 0.4406 |
87
- | 0.0741 | 14.6552 | 1700 | 0.4113 | 0.4309 |
88
- | 0.0896 | 15.5172 | 1800 | 0.4392 | 0.4308 |
89
- | 0.0492 | 16.3793 | 1900 | 0.4202 | 0.4313 |
90
- | 0.0759 | 17.2414 | 2000 | 0.4348 | 0.4207 |
91
- | 0.0406 | 18.1034 | 2100 | 0.4419 | 0.4205 |
92
- | 0.074 | 18.9655 | 2200 | 0.4306 | 0.4200 |
93
- | 0.0378 | 19.8276 | 2300 | 0.4273 | 0.4173 |
94
 
95
 
96
  ### Framework versions
97
 
98
  - Transformers 4.42.0.dev0
99
- - Pytorch 2.3.0.post300
100
  - Datasets 2.19.1
101
  - Tokenizers 0.19.1
 
1
  ---
 
2
  base_model: facebook/wav2vec2-base
3
  tags:
 
 
4
  - generated_from_trainer
5
  datasets:
6
  - timit_asr
 
13
  name: Automatic Speech Recognition
14
  type: automatic-speech-recognition
15
  dataset:
16
+ name: timit_asr
17
  type: timit_asr
18
  config: clean
19
  split: test
20
+ args: clean
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 0.4087225712464718
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  # wav2vec2-base-timit-fine-tuned
31
 
32
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the timit_asr dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.4216
35
+ - Wer: 0.4087
36
 
37
  ## Model description
38
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-------:|:----:|:---------------:|:------:|
68
+ | 3.1612 | 0.8621 | 100 | 3.1181 | 1.0 |
69
+ | 2.978 | 1.7241 | 200 | 2.9722 | 1.0 |
70
+ | 2.9185 | 2.5862 | 300 | 2.9098 | 1.0 |
71
+ | 2.1282 | 3.4483 | 400 | 2.0066 | 1.0247 |
72
+ | 1.1234 | 4.3103 | 500 | 1.0197 | 0.8393 |
73
+ | 0.602 | 5.1724 | 600 | 0.6714 | 0.6600 |
74
+ | 0.5032 | 6.0345 | 700 | 0.5285 | 0.5659 |
75
+ | 0.3101 | 6.8966 | 800 | 0.4819 | 0.5282 |
76
+ | 0.3432 | 7.7586 | 900 | 0.4653 | 0.5272 |
77
+ | 0.1922 | 8.6207 | 1000 | 0.4672 | 0.4918 |
78
+ | 0.2284 | 9.4828 | 1100 | 0.4834 | 0.4870 |
79
+ | 0.1372 | 10.3448 | 1200 | 0.4380 | 0.4727 |
80
+ | 0.1105 | 11.2069 | 1300 | 0.4509 | 0.4594 |
81
+ | 0.0992 | 12.0690 | 1400 | 0.4196 | 0.4544 |
82
+ | 0.1226 | 12.9310 | 1500 | 0.4237 | 0.4321 |
83
+ | 0.1013 | 13.7931 | 1600 | 0.4113 | 0.4298 |
84
+ | 0.0661 | 14.6552 | 1700 | 0.4038 | 0.4276 |
85
+ | 0.0901 | 15.5172 | 1800 | 0.4321 | 0.4225 |
86
+ | 0.053 | 16.3793 | 1900 | 0.4076 | 0.4236 |
87
+ | 0.0805 | 17.2414 | 2000 | 0.4336 | 0.4156 |
88
+ | 0.049 | 18.1034 | 2100 | 0.4193 | 0.4114 |
89
+ | 0.0717 | 18.9655 | 2200 | 0.4139 | 0.4091 |
90
+ | 0.0389 | 19.8276 | 2300 | 0.4216 | 0.4087 |
91
 
92
 
93
  ### Framework versions
94
 
95
  - Transformers 4.42.0.dev0
96
+ - Pytorch 2.3.0a0+git71dd2de
97
  - Datasets 2.19.1
98
  - Tokenizers 0.19.1