Model save
Browse files- README.md +68 -0
- config.json +31 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Jan23_01-30-15_Phoenix/events.out.tfevents.1705973416.Phoenix.9568.0 +3 -0
- runs/Jan23_03-39-09_Phoenix/events.out.tfevents.1705981152.Phoenix.15448.0 +3 -0
- runs/Jan23_11-09-25_Phoenix/events.out.tfevents.1706008169.Phoenix.33056.0 +3 -0
- runs/Jan23_14-39-00_Phoenix/events.out.tfevents.1706020743.Phoenix.26932.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: VIT-VoxCelebSpoof-ConstantQ-Synthetic-Voice-Detection-New
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# VIT-VoxCelebSpoof-ConstantQ-Synthetic-Voice-Detection-New
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Accuracy: 1.0
|
24 |
+
- F1: 1.0
|
25 |
+
- Loss: 0.0000
|
26 |
+
- Precision: 1.0
|
27 |
+
- Recall: 1.0
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 3.0
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:-----:|:--------:|:------:|:---------------:|:---------:|:------:|
|
58 |
+
| 0.0 | 1.0 | 29527 | 0.9999 | 0.9999 | 0.0006 | 0.9999 | 1.0 |
|
59 |
+
| 0.0 | 2.0 | 59054 | 1.0000 | 1.0000 | 0.0002 | 1.0 | 0.9999 |
|
60 |
+
| 0.0 | 3.0 | 88581 | 1.0 | 1.0 | 0.0000 | 1.0 | 1.0 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.37.0
|
66 |
+
- Pytorch 2.1.2+cu121
|
67 |
+
- Datasets 2.16.1
|
68 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Bonafide",
|
13 |
+
"1": "Spoof"
|
14 |
+
},
|
15 |
+
"image_size": 224,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"Bonafide": "0",
|
20 |
+
"Spoof": "1"
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"model_type": "vit",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_channels": 3,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"patch_size": 16,
|
28 |
+
"qkv_bias": true,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.37.0"
|
31 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:354bab37975851eba9d772406fc3e2830561d33d88d7167824b4e6f2bf9e52f4
|
3 |
+
size 343223968
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
runs/Jan23_01-30-15_Phoenix/events.out.tfevents.1705973416.Phoenix.9568.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad00f9f197a2ef49e0b39f77a6439417720df71e052858dd475c03c47451941f
|
3 |
+
size 14410
|
runs/Jan23_03-39-09_Phoenix/events.out.tfevents.1705981152.Phoenix.15448.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:074e3c518373bf50fd204bcaedc66f5e7c5898965d57c0c0594d47017332f450
|
3 |
+
size 14506
|
runs/Jan23_11-09-25_Phoenix/events.out.tfevents.1706008169.Phoenix.33056.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52c76fb8aba5d10e53e9ca3a074e82f05df0f4a5cfae1feab33c0c3ba3bdc3dc
|
3 |
+
size 14506
|
runs/Jan23_14-39-00_Phoenix/events.out.tfevents.1706020743.Phoenix.26932.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37dce1f35cd76aa04f96f0290f1f81651ac7cde14757ee023666061c3d5721bc
|
3 |
+
size 4945
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bdc01d96c339dadf434a7c45c64d78c9c1941a647effcff70f2590f9aec5c12
|
3 |
+
size 4920
|