Hugging Face's logo

van-ng
/
intent_classify

Audio Classification
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
1
van-ng commited on
Commit
c8c12e8
·
verified ·
1 Parent(s): b719d3b

Model save

Browse files
Files changed (2) hide show
  1. README.md +34 -5
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.08771929824561403
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.6443
36
- - Accuracy: 0.0877
37
 
38
  ## Model description
39
 
@@ -61,13 +61,42 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 1
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.6438 | 1.0 | 16 | 2.6443 | 0.0877 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.061946902654867256
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.7674
36
+ - Accuracy: 0.0619
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 30
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.98 | 14 | 2.6369 | 0.1062 |
71
+ | No log | 1.96 | 28 | 2.6476 | 0.0973 |
72
+ | 2.6346 | 2.95 | 42 | 2.6571 | 0.0973 |
73
+ | 2.6346 | 4.0 | 57 | 2.6573 | 0.0796 |
74
+ | 2.6206 | 4.98 | 71 | 2.6699 | 0.0708 |
75
+ | 2.6206 | 5.96 | 85 | 2.6687 | 0.0619 |
76
+ | 2.5993 | 6.95 | 99 | 2.6739 | 0.0619 |
77
+ | 2.5993 | 8.0 | 114 | 2.6755 | 0.0531 |
78
+ | 2.5752 | 8.98 | 128 | 2.6848 | 0.0619 |
79
+ | 2.5752 | 9.96 | 142 | 2.6820 | 0.0354 |
80
+ | 2.5487 | 10.95 | 156 | 2.6892 | 0.0354 |
81
+ | 2.5487 | 12.0 | 171 | 2.6989 | 0.0442 |
82
+ | 2.5112 | 12.98 | 185 | 2.7059 | 0.0354 |
83
+ | 2.5112 | 13.96 | 199 | 2.7208 | 0.0442 |
84
+ | 2.4728 | 14.95 | 213 | 2.7136 | 0.0442 |
85
+ | 2.4728 | 16.0 | 228 | 2.7208 | 0.0442 |
86
+ | 2.4331 | 16.98 | 242 | 2.7166 | 0.0265 |
87
+ | 2.4331 | 17.96 | 256 | 2.7288 | 0.0442 |
88
+ | 2.3926 | 18.95 | 270 | 2.7281 | 0.0354 |
89
+ | 2.3926 | 20.0 | 285 | 2.7297 | 0.0531 |
90
+ | 2.3926 | 20.98 | 299 | 2.7471 | 0.0531 |
91
+ | 2.341 | 21.96 | 313 | 2.7498 | 0.0619 |
92
+ | 2.341 | 22.95 | 327 | 2.7535 | 0.0619 |
93
+ | 2.2983 | 24.0 | 342 | 2.7534 | 0.0442 |
94
+ | 2.2983 | 24.98 | 356 | 2.7647 | 0.0442 |
95
+ | 2.2703 | 25.96 | 370 | 2.7696 | 0.0708 |
96
+ | 2.2703 | 26.95 | 384 | 2.7656 | 0.0531 |
97
+ | 2.238 | 28.0 | 399 | 2.7689 | 0.0619 |
98
+ | 2.238 | 28.98 | 413 | 2.7667 | 0.0619 |
99
+ | 2.213 | 29.47 | 420 | 2.7674 | 0.0619 |
100
 
101
 
102
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32fef64b204136f99f1cd3f3f10112ab4043fc703739125b7c95a4898dce5acc
3
  size 378363238
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa2e875ad858b90061fd3bfc9b85ebfaaa480332782b3f691d8229c65f61964d
3
  size 378363238