Preferred reference duration is 6 seconds not 3
Browse files
app.py
CHANGED
|
@@ -187,7 +187,7 @@ def predict(prompt, language, audio_file_pth, mic_file_path, use_mic, voice_clea
|
|
| 187 |
title = "Coqui🐸 XTTS"
|
| 188 |
|
| 189 |
description = """
|
| 190 |
-
<a href="https://huggingface.co/coqui/XTTS-v1">XTTS</a> is a Voice generation model that lets you clone voices into different languages by using just a quick
|
| 191 |
<br/>
|
| 192 |
XTTS is built on previous research, like Tortoise, with additional architectural innovations and training to make cross-language voice cloning and multilingual speech generation possible.
|
| 193 |
<br/>
|
|
|
|
| 187 |
title = "Coqui🐸 XTTS"
|
| 188 |
|
| 189 |
description = """
|
| 190 |
+
<a href="https://huggingface.co/coqui/XTTS-v1">XTTS</a> is a Voice generation model that lets you clone voices into different languages by using just a quick 6-second audio clip.
|
| 191 |
<br/>
|
| 192 |
XTTS is built on previous research, like Tortoise, with additional architectural innovations and training to make cross-language voice cloning and multilingual speech generation possible.
|
| 193 |
<br/>
|