Hugging Face's logo

Hemg
/
deeepfake-audio-Recognition-ttoo

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Hemg commited on
Commit
fdefac5
•
1 Parent(s): b7a1ed7

Model save

Browse files
Files changed (3) hide show
  1. README.md +20 -8
  2. model.safetensors +1 -1
  3. runs/Apr01_11-29-44_3b2e8eea51ac/events.out.tfevents.1711970985.3b2e8eea51ac.900.6 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8484848484848485
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 audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4021
36
- - Accuracy: 0.8485
37
 
38
  ## Model description
39
 
@@ -59,16 +59,28 @@ The following hyperparameters were used during training:
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.01
62
- - num_epochs: 4
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.6598 | 1.0 | 33 | 0.6142 | 0.6515 |
69
- | 0.5134 | 2.0 | 66 | 0.5394 | 0.7273 |
70
- | 0.3837 | 3.0 | 99 | 0.5137 | 0.7879 |
71
- | 0.3438 | 4.0 | 132 | 0.4021 | 0.8485 |
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9696969696969697
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 audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1858
36
+ - Accuracy: 0.9697
37
 
38
  ## Model description
39
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.01
62
+ - num_epochs: 16
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.6477 | 1.0 | 33 | 0.5411 | 0.8182 |
69
+ | 0.5099 | 2.0 | 66 | 0.4458 | 0.7879 |
70
+ | 0.3855 | 3.0 | 99 | 0.5405 | 0.7727 |
71
+ | 0.2943 | 4.0 | 132 | 0.2268 | 0.9394 |
72
+ | 0.2818 | 5.0 | 165 | 0.2283 | 0.9091 |
73
+ | 0.2378 | 6.0 | 198 | 0.1955 | 0.9394 |
74
+ | 0.1321 | 7.0 | 231 | 0.2335 | 0.9394 |
75
+ | 0.1688 | 8.0 | 264 | 0.2009 | 0.9545 |
76
+ | 0.07 | 9.0 | 297 | 0.2629 | 0.9242 |
77
+ | 0.0413 | 10.0 | 330 | 0.2156 | 0.9545 |
78
+ | 0.0229 | 11.0 | 363 | 0.3189 | 0.9394 |
79
+ | 0.0062 | 12.0 | 396 | 0.3850 | 0.9242 |
80
+ | 0.0159 | 13.0 | 429 | 0.2462 | 0.9394 |
81
+ | 0.0179 | 14.0 | 462 | 0.1904 | 0.9697 |
82
+ | 0.0059 | 15.0 | 495 | 0.1844 | 0.9697 |
83
+ | 0.0248 | 16.0 | 528 | 0.1858 | 0.9697 |
84
 
85
 
86
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85af37a686a4242fed092f2564c7e3acb98e65e15c4e01a6088bb1781b9a0ffb
3
  size 378302360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7806217c2cdf2b2fccfc75d129097fe0c118c96f13925bec56a2c330fc704e
3
  size 378302360
runs/Apr01_11-29-44_3b2e8eea51ac/events.out.tfevents.1711970985.3b2e8eea51ac.900.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e59e1849979164f0c854f4efcb3015dacd80ebd04bb817b78d51153b14e8a47b
3
- size 14986
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f374267ba9a2da5c37f9ec1f7785212cef66fc72fff0db6d2174d357aa8648
3
+ size 15340