Spaces:
Running
on
T4
Running
on
T4
Vaibhav Srivastav
commited on
Commit
•
e1c65f1
1
Parent(s):
fc50d18
up
Browse files
app.py
CHANGED
@@ -20,6 +20,18 @@ def predict(prompt, language, audio_file_pth):
|
|
20 |
|
21 |
title = "Coqui🐸 XTTS"
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
gr.Interface(
|
24 |
fn=predict,
|
25 |
inputs=[
|
|
|
20 |
|
21 |
title = "Coqui🐸 XTTS"
|
22 |
|
23 |
+
description = """
|
24 |
+
<p>For faster inference without waiting in the queue, you should duplicate this space and upgrade to GPU via the settings.
|
25 |
+
<br/>
|
26 |
+
<a href="https://huggingface.co/spaces/coqui/xtts?duplicate=true">
|
27 |
+
<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
|
28 |
+
</p>
|
29 |
+
XTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 3-second audio clip.
|
30 |
+
Built on Tortoise, XTTS has important model changes that make cross-language voice cloning and multi-lingual speech generation super easy.
|
31 |
+
<br/>
|
32 |
+
This is the same model that powers Coqui Studio, and Coqui API, however we apply a few tricks to make it faster and support streaming inference.
|
33 |
+
"""
|
34 |
+
|
35 |
gr.Interface(
|
36 |
fn=predict,
|
37 |
inputs=[
|