Spaces:
Running
Running
File size: 1,363 Bytes
68cfefc ae4d7aa fe77cbc 8a95680 cf7e36e fe77cbc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
import os
try:
import torchaudio
except ImportError:
os.system("cd ./F5-TTS; pip install -e .")
import spaces
import logging
from datetime import datetime
from pathlib import Path
import gradio as gr
import torch
import torchaudio
import tempfile
log = logging.getLogger()
#@spaces.GPU(duration=120)
@torch.inference_mode()
def video_to_audio(video: gr.Video, prompt: str, negative_prompt: str, seed: int, num_steps: int,
cfg_strength: float, duration: float):
os.system("bash v2a.sh")
return "v2a"
video_to_audio_tab = gr.Interface(
fn=video_to_audio,
description="""
Project page: <a href="https://hkchengrex.com/MMAudio/">https://hkchengrex.com/MMAudio/</a><br>
Code: <a href="https://github.com/acappemin/DeepAudio-V1">https://github.com/acappemin/DeepAudio-V1</a><br>
""",
inputs=[
gr.Video(),
gr.Text(label='Prompt'),
],
outputs='playable_video',
cache_examples=False,
title='MMAudio — Video-to-Audio Synthesis',
examples=[
[
'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_beach.mp4',
'',
],
])
if __name__ == "__main__":
gr.TabbedInterface([video_to_audio_tab],
['Video-to-Audio']).launch()
|