mrfakename
commited on
Commit
•
3e66674
1
Parent(s):
9b4174c
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license:
|
3 |
+
- mit
|
4 |
+
- apache-2.0
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
library_name: transformers
|
8 |
+
pipeline_tag: audio-classification
|
9 |
+
tags:
|
10 |
+
- audio
|
11 |
+
- tts
|
12 |
+
---
|
13 |
+
|
14 |
+
# StyleTTS 2 Detector
|
15 |
+
|
16 |
+
This is a model trained for audio classification on a dataset of almost 10,000 samples of human and StyleTTS 2-generated audio clips. The model is based on [Whisper](https://huggingface.co/openai/whisper-base).
|
17 |
+
|
18 |
+
**NOTE: This model is not affiliated with the author(s) of StyleTTS 2 in any way.**
|
19 |
+
|
20 |
+
## Online Demo
|
21 |
+
|
22 |
+
An online demo is available [here].
|
23 |
+
|
24 |
+
## Usage
|
25 |
+
|
26 |
+
**IMPORTANT:** Please read the license, disclaimer, and model card before using the model. You may not use the model if you do not agree to the license and disclaimer.
|
27 |
+
|
28 |
+
```python
|
29 |
+
from transformers import pipeline
|
30 |
+
import torch
|
31 |
+
|
32 |
+
pipe = pipeline('audio-classification', model='mrfakename/styletts2-detector', device='cuda' if torch.cuda.is_available() else 'cpu')
|
33 |
+
|
34 |
+
result = pipe('audio.wav')
|
35 |
+
|
36 |
+
print(result)
|
37 |
+
```
|
38 |
+
|
39 |
+
## Tags
|
40 |
+
|
41 |
+
The audio will be classified as either `real` or `fake` (human-generated or StyleTTS 2-spoken).
|
42 |
+
|
43 |
+
## Disclaimer
|
44 |
+
|
45 |
+
The author(s) of this model cannot guarantee complete accuracy. False positives or negatives may occur.
|
46 |
+
|
47 |
+
Usage of this model should not replace other precautions, such as invisible watermarking or audio watermarking.
|
48 |
+
|
49 |
+
This model has been trained on outputs from the StyleTTS 2 base model, not fine-tunes. The model may not identify fine-tunes properly.
|
50 |
+
|
51 |
+
The author(s) of this model disclaim all liability related to or in connection with the usage of this model.
|
52 |
+
|
53 |
+
## License
|
54 |
+
|
55 |
+
You may use this model under the **MIT** or **Apache 2.0** license, at your choice, so long as you include the disclaimer above in all redistributions, and require all future redistributions to include the disclaimer.
|