Hugging Face's logo

MuhammadIqbalBazmi
/
wav2vec2-base-intent-classification-ori

Audio Classification
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
MuhammadIqbalBazmi commited on
Commit
260fb54
•
1 Parent(s): 6beca1c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -51
README.md CHANGED
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # wav2vec2-base-intent-classification-ori
16
 
17
- This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the [intent-dataset](https://huggingface.co/datasets/MuhammadIqbalBazmi/intent-dataset) dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6860
20
- - Accuracy: 0.7917
21
 
22
  ## Model description
23
 
@@ -37,11 +37,11 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 3e-05
40
- - train_batch_size: 2
41
- - eval_batch_size: 2
42
  - seed: 42
43
  - gradient_accumulation_steps: 4
44
- - total_train_batch_size: 8
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
@@ -51,51 +51,51 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 2.1955 | 1.0 | 14 | 2.1826 | 0.25 |
55
- | 2.1863 | 2.0 | 28 | 2.1211 | 0.3333 |
56
- | 2.1137 | 3.0 | 42 | 2.0599 | 0.3333 |
57
- | 2.0855 | 4.0 | 56 | 2.0110 | 0.3333 |
58
- | 2.02 | 5.0 | 70 | 1.8870 | 0.3958 |
59
- | 1.9762 | 6.0 | 84 | 1.7885 | 0.4375 |
60
- | 1.8745 | 7.0 | 98 | 1.7575 | 0.4583 |
61
- | 1.7797 | 8.0 | 112 | 1.7475 | 0.4375 |
62
- | 1.7613 | 9.0 | 126 | 1.4668 | 0.5417 |
63
- | 1.5637 | 10.0 | 140 | 1.3769 | 0.4583 |
64
- | 1.4365 | 11.0 | 154 | 1.4320 | 0.4792 |
65
- | 1.4563 | 12.0 | 168 | 1.3770 | 0.5 |
66
- | 1.2626 | 13.0 | 182 | 1.2775 | 0.5208 |
67
- | 1.2228 | 14.0 | 196 | 1.3321 | 0.4792 |
68
- | 1.14 | 15.0 | 210 | 1.1823 | 0.5417 |
69
- | 1.0518 | 16.0 | 224 | 1.2527 | 0.4792 |
70
- | 1.1248 | 17.0 | 238 | 1.0706 | 0.625 |
71
- | 0.917 | 18.0 | 252 | 1.0176 | 0.6042 |
72
- | 0.8725 | 19.0 | 266 | 1.0971 | 0.5833 |
73
- | 0.7962 | 20.0 | 280 | 0.9867 | 0.6042 |
74
- | 0.7203 | 21.0 | 294 | 0.8614 | 0.6667 |
75
- | 0.5947 | 22.0 | 308 | 0.8979 | 0.6875 |
76
- | 0.5722 | 23.0 | 322 | 0.8487 | 0.6667 |
77
- | 0.5088 | 24.0 | 336 | 0.8713 | 0.625 |
78
- | 0.4422 | 25.0 | 350 | 0.6776 | 0.8333 |
79
- | 0.4164 | 26.0 | 364 | 0.6572 | 0.8125 |
80
- | 0.3846 | 27.0 | 378 | 0.7982 | 0.7083 |
81
- | 0.331 | 28.0 | 392 | 0.7706 | 0.7708 |
82
- | 0.2883 | 29.0 | 406 | 0.7989 | 0.6875 |
83
- | 0.2318 | 30.0 | 420 | 0.5795 | 0.8125 |
84
- | 0.2155 | 31.0 | 434 | 0.6404 | 0.8125 |
85
- | 0.2071 | 32.0 | 448 | 0.7110 | 0.7708 |
86
- | 0.1691 | 33.0 | 462 | 0.7089 | 0.7917 |
87
- | 0.1676 | 34.0 | 476 | 0.6462 | 0.8125 |
88
- | 0.1418 | 35.0 | 490 | 0.6559 | 0.8125 |
89
- | 0.1324 | 36.0 | 504 | 0.6449 | 0.8125 |
90
- | 0.1503 | 37.0 | 518 | 0.6334 | 0.8125 |
91
- | 0.1193 | 38.0 | 532 | 0.6347 | 0.8125 |
92
- | 0.123 | 39.0 | 546 | 0.6336 | 0.8125 |
93
- | 0.1109 | 40.0 | 560 | 0.6892 | 0.7917 |
94
- | 0.1025 | 41.0 | 574 | 0.7381 | 0.7708 |
95
- | 0.1122 | 42.0 | 588 | 0.7132 | 0.7917 |
96
- | 0.1041 | 43.0 | 602 | 0.6976 | 0.7917 |
97
- | 0.1074 | 44.0 | 616 | 0.6883 | 0.7917 |
98
- | 0.102 | 45.0 | 630 | 0.6860 | 0.7917 |
99
 
100
 
101
  ### Framework versions
 
14
 
15
  # wav2vec2-base-intent-classification-ori
16
 
17
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6214
20
+ - Accuracy: 0.8542
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 3e-05
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 1
42
  - seed: 42
43
  - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 4
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 2.1969 | 1.0 | 28 | 2.1823 | 0.1667 |
55
+ | 2.1258 | 2.0 | 56 | 2.1160 | 0.2708 |
56
+ | 2.1138 | 3.0 | 84 | 2.1125 | 0.3125 |
57
+ | 2.038 | 4.0 | 112 | 2.0132 | 0.2708 |
58
+ | 2.0267 | 5.0 | 140 | 2.0051 | 0.3333 |
59
+ | 1.8788 | 6.0 | 168 | 1.8372 | 0.4167 |
60
+ | 1.8875 | 7.0 | 196 | 1.9644 | 0.2917 |
61
+ | 1.7334 | 8.0 | 224 | 1.5419 | 0.5625 |
62
+ | 1.3128 | 9.0 | 252 | 1.5499 | 0.4792 |
63
+ | 1.1863 | 10.0 | 280 | 1.4967 | 0.4792 |
64
+ | 1.2418 | 11.0 | 308 | 1.3421 | 0.5625 |
65
+ | 1.2286 | 12.0 | 336 | 1.1493 | 0.5625 |
66
+ | 1.087 | 13.0 | 364 | 1.2001 | 0.5625 |
67
+ | 0.7581 | 14.0 | 392 | 1.2114 | 0.6042 |
68
+ | 0.7801 | 15.0 | 420 | 0.8873 | 0.7292 |
69
+ | 0.6041 | 16.0 | 448 | 1.0526 | 0.75 |
70
+ | 0.4093 | 17.0 | 476 | 0.8694 | 0.6875 |
71
+ | 0.36 | 18.0 | 504 | 0.6712 | 0.7917 |
72
+ | 0.3617 | 19.0 | 532 | 0.7221 | 0.7708 |
73
+ | 0.2808 | 20.0 | 560 | 0.5851 | 0.8333 |
74
+ | 0.192 | 21.0 | 588 | 0.5821 | 0.8125 |
75
+ | 0.1924 | 22.0 | 616 | 0.5993 | 0.7917 |
76
+ | 0.3129 | 23.0 | 644 | 0.6615 | 0.7708 |
77
+ | 0.1542 | 24.0 | 672 | 0.8268 | 0.7292 |
78
+ | 0.1038 | 25.0 | 700 | 0.4629 | 0.875 |
79
+ | 0.0749 | 26.0 | 728 | 0.5098 | 0.8542 |
80
+ | 0.043 | 27.0 | 756 | 0.5493 | 0.8333 |
81
+ | 0.0521 | 28.0 | 784 | 0.5119 | 0.8542 |
82
+ | 0.0411 | 29.0 | 812 | 0.5280 | 0.875 |
83
+ | 0.04 | 30.0 | 840 | 0.5243 | 0.875 |
84
+ | 0.0341 | 31.0 | 868 | 0.5478 | 0.875 |
85
+ | 0.0313 | 32.0 | 896 | 0.5489 | 0.875 |
86
+ | 0.0271 | 33.0 | 924 | 0.5563 | 0.875 |
87
+ | 0.0261 | 34.0 | 952 | 0.5735 | 0.875 |
88
+ | 0.0223 | 35.0 | 980 | 0.5748 | 0.8542 |
89
+ | 0.0235 | 36.0 | 1008 | 0.6004 | 0.8542 |
90
+ | 0.0229 | 37.0 | 1036 | 0.6360 | 0.8542 |
91
+ | 0.0935 | 38.0 | 1064 | 0.6190 | 0.8542 |
92
+ | 0.0215 | 39.0 | 1092 | 0.6138 | 0.8542 |
93
+ | 0.0237 | 40.0 | 1120 | 0.6231 | 0.8542 |
94
+ | 0.0219 | 41.0 | 1148 | 0.6197 | 0.8542 |
95
+ | 0.0236 | 42.0 | 1176 | 0.6207 | 0.8542 |
96
+ | 0.021 | 43.0 | 1204 | 0.6189 | 0.8542 |
97
+ | 0.021 | 44.0 | 1232 | 0.6204 | 0.8542 |
98
+ | 0.0217 | 45.0 | 1260 | 0.6214 | 0.8542 |
99
 
100
 
101
  ### Framework versions