Update README.md
Browse files
README.md
CHANGED
@@ -20,4 +20,37 @@ tags:
|
|
20 |
- vc
|
21 |
- svc
|
22 |
- multilingual
|
23 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
- vc
|
21 |
- svc
|
22 |
- multilingual
|
23 |
+
---
|
24 |
+
|
25 |
+
# FreeSVC: Zero-shot Multilingual Singing Voice Conversion
|
26 |
+
|
27 |
+
**FreeSVC** is a state-of-the-art multilingual singing voice conversion model designed for zero-shot learning. It enables the conversion of singing voices across various languages without the need for extensive language-specific training.
|
28 |
+
|
29 |
+
## Supported Languages
|
30 |
+
|
31 |
+
FreeSVC supports the following languages:
|
32 |
+
|
33 |
+
```yaml
|
34 |
+
lang2id:
|
35 |
+
chinese: 0
|
36 |
+
dutch: 1
|
37 |
+
english: 2
|
38 |
+
french: 3
|
39 |
+
german: 4
|
40 |
+
italian: 5
|
41 |
+
japanese: 6
|
42 |
+
other: 7 # Vocal techniques
|
43 |
+
polish: 8
|
44 |
+
portuguese: 9
|
45 |
+
spanish: 10
|
46 |
+
```
|
47 |
+
Note: The "other" category includes various vocal techniques.
|
48 |
+
|
49 |
+
## Model Overview
|
50 |
+
FreeSVC leverages an enhanced VITS architecture integrated with Speaker-invariant Clustering (SPIN) and the ECAPA2 speaker encoder. This combination effectively separates speaker characteristics from linguistic content, ensuring high-quality and natural-sounding voice conversions across multiple languages.
|
51 |
+
|
52 |
+
## Original Repository
|
53 |
+
For more detailed information, please visit the [original GitHub repository](https://github.com/freds0/free-svc).
|
54 |
+
|
55 |
+
## License
|
56 |
+
This project is licensed under the MIT License.
|