Update README.md
Browse files
README.md
CHANGED
|
@@ -54,20 +54,20 @@ FreeSVC leverages an enhanced VITS architecture integrated with Speaker-invarian
|
|
| 54 |
FreeSVC was trained on a diverse set of speech and singing datasets covering multiple languages:
|
| 55 |
|
| 56 |
| **Dataset** | **Hours** | **Language** | **Type** |
|
| 57 |
-
|
| 58 |
-
| AISHELL-1 | 170h
|
| 59 |
-
| AISHELL-3 | 85h
|
| 60 |
-
| CML-TTS | 3.1k
|
| 61 |
-
| HiFiTTS | 292h
|
| 62 |
-
| JVS | 30h
|
| 63 |
-
| LibriTTS-R | 585h
|
| 64 |
-
| NUS (NHSS) | 7h
|
| 65 |
-
| OpenSinger | 50h
|
| 66 |
-
| Opencpop | 5h
|
| 67 |
-
| PopBuTFy | 10h, 40h
|
| 68 |
-
| POPCS | 5h
|
| 69 |
-
| VCTK | 44h
|
| 70 |
-
| VocalSet | 10h
|
| 71 |
|
| 72 |
## Original Repository
|
| 73 |
For more detailed information, please visit the [original GitHub repository](https://github.com/freds0/free-svc).
|
|
|
|
| 54 |
FreeSVC was trained on a diverse set of speech and singing datasets covering multiple languages:
|
| 55 |
|
| 56 |
| **Dataset** | **Hours** | **Language** | **Type** |
|
| 57 |
+
|----------------------|------------|--------------|--------------|
|
| 58 |
+
| AISHELL-1 | 170h | Chinese | Speech |
|
| 59 |
+
| AISHELL-3 | 85h | Chinese | Speech |
|
| 60 |
+
| CML-TTS | 3.1k | 7 Languages | Speech |
|
| 61 |
+
| HiFiTTS | 292h | English | Speech |
|
| 62 |
+
| JVS | 30h | Japanese | Speech |
|
| 63 |
+
| LibriTTS-R | 585h | English | Speech |
|
| 64 |
+
| NUS (NHSS) | 7h | English | Both |
|
| 65 |
+
| OpenSinger | 50h | Chinese | Singing |
|
| 66 |
+
| Opencpop | 5h | Chinese | Singing |
|
| 67 |
+
| PopBuTFy | 10h, 40h | Chinese, English | Singing |
|
| 68 |
+
| POPCS | 5h | Chinese | Singing |
|
| 69 |
+
| VCTK | 44h | English | Speech |
|
| 70 |
+
| VocalSet | 10h | Other | Singing |
|
| 71 |
|
| 72 |
## Original Repository
|
| 73 |
For more detailed information, please visit the [original GitHub repository](https://github.com/freds0/free-svc).
|