Hugging Face's logo

cloudwalkerw
/
wavlm-base_3

Audio Classification
Transformers
PyTorch
wavlm
Generated from Trainer
Inference Endpoints
Model card Files Community
1
cloudwalkerw commited on
Commit
58032f9
·
1 Parent(s): aa2f9bc

Model save

Browse files
Files changed (2) hide show
  1. README.md +10 -42
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -1,7 +1,6 @@
1
  ---
2
  base_model: microsoft/wavlm-base
3
  tags:
4
- - audio-classification
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
@@ -17,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3295
21
- - Accuracy: 0.8974
22
 
23
  ## Model description
24
 
@@ -52,45 +51,14 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.4161 | 0.25 | 100 | 0.3295 | 0.8974 |
56
- | 0.3196 | 0.5 | 200 | 0.3312 | 0.8974 |
57
- | 0.3391 | 0.76 | 300 | 0.3353 | 0.8974 |
58
- | 0.3285 | 1.01 | 400 | 0.3322 | 0.8974 |
59
- | 0.3354 | 1.26 | 500 | 0.3366 | 0.8974 |
60
- | 0.3344 | 1.51 | 600 | 0.3315 | 0.8974 |
61
- | 0.3343 | 1.76 | 700 | 0.3308 | 0.8974 |
62
- | 0.325 | 2.02 | 800 | 0.3382 | 0.8974 |
63
- | 0.34 | 2.27 | 900 | 0.3314 | 0.8974 |
64
- | 0.3333 | 2.52 | 1000 | 0.3388 | 0.8974 |
65
- | 0.318 | 2.77 | 1100 | 0.3371 | 0.8974 |
66
- | 0.3281 | 3.02 | 1200 | 0.3362 | 0.8974 |
67
- | 0.3293 | 3.28 | 1300 | 0.3307 | 0.8974 |
68
- | 0.3175 | 3.53 | 1400 | 0.3357 | 0.8974 |
69
- | 0.3415 | 3.78 | 1500 | 0.3321 | 0.8974 |
70
- | 0.341 | 4.03 | 1600 | 0.3307 | 0.8974 |
71
- | 0.3285 | 4.28 | 1700 | 0.3308 | 0.8974 |
72
- | 0.3337 | 4.54 | 1800 | 0.3308 | 0.8974 |
73
- | 0.3276 | 4.79 | 1900 | 0.3307 | 0.8974 |
74
- | 0.3248 | 5.04 | 2000 | 0.3311 | 0.8974 |
75
- | 0.3371 | 5.29 | 2100 | 0.3317 | 0.8974 |
76
- | 0.3261 | 5.55 | 2200 | 0.3315 | 0.8974 |
77
- | 0.3277 | 5.8 | 2300 | 0.3323 | 0.8974 |
78
- | 0.3297 | 6.05 | 2400 | 0.3321 | 0.8974 |
79
- | 0.3397 | 6.3 | 2500 | 0.3316 | 0.8974 |
80
- | 0.3313 | 6.55 | 2600 | 0.3376 | 0.8974 |
81
- | 0.3297 | 6.81 | 2700 | 0.3326 | 0.8974 |
82
- | 0.3148 | 7.06 | 2800 | 0.3326 | 0.8974 |
83
- | 0.33 | 7.31 | 2900 | 0.3307 | 0.8974 |
84
- | 0.3373 | 7.56 | 3000 | 0.3358 | 0.8974 |
85
- | 0.3229 | 7.81 | 3100 | 0.3315 | 0.8974 |
86
- | 0.3311 | 8.07 | 3200 | 0.3330 | 0.8974 |
87
- | 0.32 | 8.32 | 3300 | 0.3329 | 0.8974 |
88
- | 0.3303 | 8.57 | 3400 | 0.3333 | 0.8974 |
89
- | 0.3268 | 8.82 | 3500 | 0.3325 | 0.8974 |
90
- | 0.3362 | 9.07 | 3600 | 0.3314 | 0.8974 |
91
- | 0.3391 | 9.33 | 3700 | 0.3309 | 0.8974 |
92
- | 0.3233 | 9.58 | 3800 | 0.3319 | 0.8974 |
93
- | 0.3196 | 9.83 | 3900 | 0.3325 | 0.8974 |
94
 
95
 
96
  ### Framework versions
 
1
  ---
2
  base_model: microsoft/wavlm-base
3
  tags:
 
4
  - generated_from_trainer
5
  metrics:
6
  - accuracy
 
16
 
17
  This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7129
20
+ - Accuracy: 0.1026
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.2236 | 1.24 | 100 | 12.8495 | 0.4467 |
55
+ | 0.0514 | 2.48 | 200 | 16.3078 | 0.2677 |
56
+ | 0.0 | 3.72 | 300 | 17.5651 | 0.2597 |
57
+ | 0.3252 | 4.95 | 400 | 15.0382 | 0.1912 |
58
+ | 1.0577 | 6.19 | 500 | 0.6534 | 0.8974 |
59
+ | 0.6973 | 7.43 | 600 | 0.7352 | 0.1026 |
60
+ | 0.6939 | 8.67 | 700 | 0.6210 | 0.8974 |
61
+ | 0.6944 | 9.91 | 800 | 0.7129 | 0.1026 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0a7768777c18bb230b40904dc39cae0d907543593407a11bb7025c0063d8a8e
3
  size 378402813
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923826c892e8069448904946ade5daf9ac9a68ec627472bc76a32cc9e3c671e2
3
  size 378402813