Readd description
Browse files
app.py
CHANGED
|
@@ -103,7 +103,21 @@ def predict(prompt, language, audio_file_pth, mic_file_path, use_mic, agree, req
|
|
| 103 |
|
| 104 |
title = "XTTS Glz's remake (Fonctional Text-2-Speech)"
|
| 105 |
|
| 106 |
-
description = ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
|
| 108 |
article = """
|
| 109 |
<div style='margin:20px auto;'>
|
|
|
|
| 103 |
|
| 104 |
title = "XTTS Glz's remake (Fonctional Text-2-Speech)"
|
| 105 |
|
| 106 |
+
description = f"""
|
| 107 |
+
<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 3-second audio clip.
|
| 108 |
+
<br/>
|
| 109 |
+
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.
|
| 110 |
+
<br/>
|
| 111 |
+
This is the same model that powers our creator application <a href="https://coqui.ai">Coqui Studio</a> as well as the <a href="https://docs.coqui.ai">Coqui API</a>. In production we apply modifications to make low-latency streaming possible.
|
| 112 |
+
<br/>
|
| 113 |
+
Leave a star on the Github <a href="https://github.com/coqui-ai/TTS">TTS</a>, where our open-source inference and training code lives.
|
| 114 |
+
<br/>
|
| 115 |
+
<p>For faster inference without waiting in the queue, you should duplicate this space and upgrade to GPU via the settings.
|
| 116 |
+
<br/>
|
| 117 |
+
<a href="https://huggingface.co/spaces/coqui/xtts?duplicate=true">
|
| 118 |
+
<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
|
| 119 |
+
</p>
|
| 120 |
+
"""
|
| 121 |
|
| 122 |
article = """
|
| 123 |
<div style='margin:20px auto;'>
|