Spaces:
Configuration error
Configuration error
Update app.py
Browse files
app.py
CHANGED
|
@@ -76,6 +76,22 @@ demo = gr.Interface(
|
|
| 76 |
inputs=demo_inputs,
|
| 77 |
outputs=demo_outputs,
|
| 78 |
title="NaturalSpeech3 FACodec",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
)
|
| 80 |
|
| 81 |
if __name__ == "__main__":
|
|
|
|
| 76 |
inputs=demo_inputs,
|
| 77 |
outputs=demo_outputs,
|
| 78 |
title="NaturalSpeech3 FACodec",
|
| 79 |
+
description=
|
| 80 |
+
"""
|
| 81 |
+
## FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3
|
| 82 |
+
|
| 83 |
+
[](https://arxiv.org/pdf/2403.03100.pdf)
|
| 84 |
+
|
| 85 |
+
[](https://speechresearch.github.io/naturalspeech3/)
|
| 86 |
+
|
| 87 |
+
[](https://huggingface.co/amphion/naturalspeech3_facodec)
|
| 88 |
+
|
| 89 |
+
## Overview
|
| 90 |
+
|
| 91 |
+
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.
|
| 92 |
+
|
| 93 |
+
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).
|
| 94 |
+
""",
|
| 95 |
)
|
| 96 |
|
| 97 |
if __name__ == "__main__":
|