Hugging Face's logo

motheecreator
/
wav2vec2-base-finetuned-ks

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
motheecreator commited on
Commit
a2b4afb
•
1 Parent(s): 7a594ea

End of training

Browse files
Files changed (6) hide show
  1. README.md +16 -18
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Apr18_06-34-21_f2716b2ef694/events.out.tfevents.1713422097.f2716b2ef694.34.0 +3 -0
  5. runs/Apr18_06-34-21_f2716b2ef694/events.out.tfevents.1713424477.f2716b2ef694.34.1 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -1,30 +1,28 @@
1
  ---
2
  license: apache-2.0
3
- base_model: facebook/wav2vec2-base
4
  tags:
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
  - name: wav2vec2-base-finetuned-ks
10
  results:
11
  - task:
12
- name: DeepFake audio detection
13
  type: audio-classification
14
  dataset:
15
- name: Fake or Real
16
- type: Audio
17
  config: default
18
  split: validation
19
  args: default
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
- value: 0.9994443415447305
24
- language:
25
- - en
26
- library_name: transformers
27
- pipeline_tag: audio-classification
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  # wav2vec2-base-finetuned-ks
34
 
35
- This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the Fake or Real (FoR) dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.0031
38
- - Accuracy: 0.9994
39
 
40
  ## Model description
41
 
@@ -69,11 +67,11 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
72
- | 0.0085 | 1.0 | 421 | 0.0133 | 0.9977 |
73
- | 0.0005 | 2.0 | 842 | 0.0060 | 0.9986 |
74
- | 0.0002 | 3.0 | 1263 | 0.0031 | 0.9994 |
75
- | 0.0002 | 4.0 | 1684 | 0.0033 | 0.9993 |
76
- | 0.0001 | 5.0 | 2105 | 0.0028 | 0.9994 |
77
 
78
 
79
  ### Framework versions
@@ -81,4 +79,4 @@ The following hyperparameters were used during training:
81
  - Transformers 4.39.3
82
  - Pytorch 2.1.2
83
  - Datasets 2.18.0
84
- - Tokenizers 0.15.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: motheecreator/wav2vec2-base-finetuned-ks
4
  tags:
5
  - generated_from_trainer
6
+ datasets:
7
+ - audiofolder
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: wav2vec2-base-finetuned-ks
12
  results:
13
  - task:
14
+ name: Audio Classification
15
  type: audio-classification
16
  dataset:
17
+ name: audiofolder
18
+ type: audiofolder
19
  config: default
20
  split: validation
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9982174688057041
 
 
 
 
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # wav2vec2-base-finetuned-ks
32
 
33
+ This model is a fine-tuned version of [motheecreator/wav2vec2-base-finetuned-ks](https://huggingface.co/motheecreator/wav2vec2-base-finetuned-ks) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.0117
36
+ - Accuracy: 0.9982
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.0528 | 0.99 | 79 | 0.0318 | 0.9947 |
71
+ | 0.0246 | 1.99 | 159 | 0.0132 | 0.9978 |
72
+ | 0.0142 | 3.0 | 239 | 0.0158 | 0.9978 |
73
+ | 0.007 | 4.0 | 319 | 0.0117 | 0.9982 |
74
+ | 0.0004 | 4.95 | 395 | 0.0147 | 0.9982 |
75
 
76
 
77
  ### Framework versions
 
79
  - Transformers 4.39.3
80
  - Pytorch 2.1.2
81
  - Datasets 2.18.0
82
+ - Tokenizers 0.15.2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "facebook/wav2vec2-base",
3
  "activation_dropout": 0.0,
4
  "adapter_attn_dim": null,
5
  "adapter_kernel_size": 3,
 
1
  {
2
+ "_name_or_path": "motheecreator/wav2vec2-base-finetuned-ks",
3
  "activation_dropout": 0.0,
4
  "adapter_attn_dim": null,
5
  "adapter_kernel_size": 3,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:405e6b51874ae7922050ef0918ffbd86188bebb3801283bdd8141ff9331e2fe8
3
  size 378302360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d71a2ba7bf35a75c8dc89cdf1a9c81c85c7266d576b44d7d2cb3822ae7f6bb3
3
  size 378302360
runs/Apr18_06-34-21_f2716b2ef694/events.out.tfevents.1713422097.f2716b2ef694.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b7128dbda69fcd3df04a7a1d5479a611adaf88a2003f4086b5884e27b58bc9a
3
+ size 16653
runs/Apr18_06-34-21_f2716b2ef694/events.out.tfevents.1713424477.f2716b2ef694.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e895154e69f1bd9516a674adbe2f145ed33b7e98a0ee6ff4b76e4ae575a9eb
3
+ size 411
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc6602863174aec8eb964caea8c7925627ffd55918d0a6fc55e1875fd99b6b4c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d859514321e2c31c44263628856660276831db71641c58db61d385eac5dfa3a
3
  size 4984