Spaces:
Running
on
L4
Running
on
L4
wanglamao
commited on
Commit
·
71de750
1
Parent(s):
8220abd
change style
Browse files- .gitignore +1 -0
- app.py +35 -3
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
__pycache__
|
app.py
CHANGED
|
@@ -105,9 +105,24 @@ theme = gr.themes.Soft(
|
|
| 105 |
font=[gr.themes.GoogleFont("Inter"), "ui-sans-serif", "system-ui", "sans-serif"],
|
| 106 |
)
|
| 107 |
|
| 108 |
-
with gr.Blocks(
|
| 109 |
-
|
| 110 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
|
| 112 |
with gr.Tabs():
|
| 113 |
|
|
@@ -121,6 +136,23 @@ with gr.Blocks(title="General Purpose Audio System", theme=theme) as demo:
|
|
| 121 |
ttsa_btn = gr.Button("Synthesize Now", variant="primary")
|
| 122 |
ttsa_btn.click(process_tts_a, inputs=[ttsa_text, ttsa_ref], outputs=ttsa_output)
|
| 123 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
# --- VC Tab ---
|
| 125 |
with gr.TabItem("🎭 Voice Conversion (VC)"):
|
| 126 |
with gr.Row():
|
|
|
|
| 105 |
font=[gr.themes.GoogleFont("Inter"), "ui-sans-serif", "system-ui", "sans-serif"],
|
| 106 |
)
|
| 107 |
|
| 108 |
+
with gr.Blocks(
|
| 109 |
+
title="General Purpose Audio System",
|
| 110 |
+
theme=theme,
|
| 111 |
+
) as demo:
|
| 112 |
+
gr.Markdown(
|
| 113 |
+
"# GPA: One Model for Speech Recognition, Text-to-Speech, and Voice Conversion"
|
| 114 |
+
)
|
| 115 |
+
gr.HTML(
|
| 116 |
+
"""
|
| 117 |
+
<div style="display: flex; flex-wrap: nowrap; gap: 8px; overflow-x: auto;">
|
| 118 |
+
<a href="https://arxiv.org/abs/2601.10770"><img src="https://img.shields.io/badge/ArXiv-2601.10770-b31b1b?style=for-the-badge&logo=arxiv" alt="ArXiv"></a>
|
| 119 |
+
<a href="https://autoark.github.io/GPA/"><img src="https://img.shields.io/badge/Demo-GitHub%20Pages-blue?style=for-the-badge&logo=github" alt="Demo"></a>
|
| 120 |
+
<a href="https://huggingface.co/AutoArk-AI/GPA"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-yellow?style=for-the-badge" alt="Hugging Face"></a>
|
| 121 |
+
<a href="https://huggingface.co/spaces/AutoArk-AI/GPA_DEMO"><img src="https://img.shields.io/badge/🎮%20Interactive%20Demo-Try%20It!-blue?style=for-the-badge" alt="Interactive Demo"></a>
|
| 122 |
+
<a href="https://www.modelscope.cn/models/AutoArk/GPA"><img src="https://img.shields.io/badge/🤖%20ModelScope-Models-purple?style=for-the-badge" alt="ModelScope"></a>
|
| 123 |
+
</div>
|
| 124 |
+
"""
|
| 125 |
+
)
|
| 126 |
|
| 127 |
with gr.Tabs():
|
| 128 |
|
|
|
|
| 136 |
ttsa_btn = gr.Button("Synthesize Now", variant="primary")
|
| 137 |
ttsa_btn.click(process_tts_a, inputs=[ttsa_text, ttsa_ref], outputs=ttsa_output)
|
| 138 |
|
| 139 |
+
gr.Examples(
|
| 140 |
+
examples=[
|
| 141 |
+
[
|
| 142 |
+
"Hello, I am generated by voice cloning.",
|
| 143 |
+
"examples/tts/01/prompt.wav",
|
| 144 |
+
],
|
| 145 |
+
[
|
| 146 |
+
"Welcome to the General Purpose Audio System.",
|
| 147 |
+
"examples/tts/02/prompt.wav",
|
| 148 |
+
],
|
| 149 |
+
],
|
| 150 |
+
inputs=[ttsa_text, ttsa_ref],
|
| 151 |
+
outputs=ttsa_output,
|
| 152 |
+
fn=process_tts_a,
|
| 153 |
+
cache_examples=True,
|
| 154 |
+
)
|
| 155 |
+
|
| 156 |
# --- VC Tab ---
|
| 157 |
with gr.TabItem("🎭 Voice Conversion (VC)"):
|
| 158 |
with gr.Row():
|