Spaces:
Running
on
Zero
Running
on
Zero
Hecheng0625
commited on
Commit
•
9730071
1
Parent(s):
7634b6c
Update app.py
Browse files
app.py
CHANGED
@@ -135,27 +135,54 @@ demo_outputs = [
|
|
135 |
gr.Audio(label="Voice conversion result"),
|
136 |
]
|
137 |
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
|
147 |
-
|
148 |
-
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
159 |
|
160 |
if __name__ == "__main__":
|
161 |
demo.launch()
|
|
|
135 |
gr.Audio(label="Voice conversion result"),
|
136 |
]
|
137 |
|
138 |
+
with gr.Blocks() as demo:
|
139 |
+
gr.Interface(
|
140 |
+
fn=codec_voice_conversion,
|
141 |
+
inputs=demo_inputs,
|
142 |
+
outputs=demo_outputs,
|
143 |
+
title="NaturalSpeech3 FACodec",
|
144 |
+
description="""
|
145 |
+
## FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3
|
146 |
+
|
147 |
+
[![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/pdf/2403.03100.pdf)
|
148 |
+
|
149 |
+
[![demo](https://img.shields.io/badge/FACodec-Demo-red)](https://speechresearch.github.io/naturalspeech3/)
|
150 |
+
|
151 |
+
[![model](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Models-pink)](https://huggingface.co/amphion/naturalspeech3_facodec)
|
152 |
+
|
153 |
+
## Overview
|
154 |
+
|
155 |
+
FACodec is a core component of the advanced text-to-speech (TTS) model NaturalSpeech 3. FACodec converts complex speech waveform into disentangled subspaces representing speech attributes of content, prosody, timbre, and acoustic details and reconstruct high-quality speech waveform from these attributes. FACodec decomposes complex speech into subspaces representing different attributes, thus simplifying the modeling of speech representation.
|
156 |
+
|
157 |
+
Research can use FACodec to develop different modes of TTS models, such as non-autoregressive based discrete diffusion (NaturalSpeech 3) or autoregressive models (like VALL-E).
|
158 |
+
""",
|
159 |
+
)
|
160 |
+
|
161 |
+
gr.Examples(
|
162 |
+
examples=[
|
163 |
+
[
|
164 |
+
"default/ref/1.wav",
|
165 |
+
"default/source/1.wav",
|
166 |
+
],
|
167 |
+
[
|
168 |
+
"default/ref/2.wav",
|
169 |
+
"default/source/2.wav",
|
170 |
+
],
|
171 |
+
[
|
172 |
+
"default/ref/3.wav",
|
173 |
+
"default/source/3.wav",
|
174 |
+
],
|
175 |
+
[
|
176 |
+
"default/ref/4.wav",
|
177 |
+
"default/source/4.wav",
|
178 |
+
],
|
179 |
+
[
|
180 |
+
"default/ref/5.wav",
|
181 |
+
"default/source/5.wav",
|
182 |
+
],
|
183 |
+
],
|
184 |
+
inputs=demo_inputs,
|
185 |
+
)
|
186 |
|
187 |
if __name__ == "__main__":
|
188 |
demo.launch()
|