Spaces:
Sleeping
Sleeping
File size: 1,630 Bytes
1a53a31 649918e 1a53a31 649918e 1a53a31 649918e 1a53a31 d2f72d2 1a53a31 d2f72d2 1a53a31 d2f72d2 1a53a31 649918e d2f72d2 1a53a31 649918e 1a53a31 d2f72d2 649918e 1a53a31 649918e 1a53a31 649918e |
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 |
import gradio as gr
import requests
import soundfile as sf
import io
import torch
import torchaudio
API_URL = "https://hf.space/embed/akhaliq/denoise-audio/+/api/predict"
def enhance_vo(file, denoise_strength):
# Step 1: Read audio and send to remote model
with open(file, "rb") as f:
response = requests.post(API_URL, files={"data": f})
if response.status_code != 200:
raise Exception("Denoising model failed to process audio.")
# Step 2: Get denoised audio back
response_data = response.json()
url = response_data["data"][0]["url"]
audio_response = requests.get(url)
denoised_bytes = io.BytesIO(audio_response.content)
# Step 3: Load both original and denoised audio
orig_waveform, sr = torchaudio.load(file)
denoised_waveform, _ = torchaudio.load(denoised_bytes)
# Step 4: Blend based on slider value
blend_ratio = denoise_strength / 100.0
output = (1 - blend_ratio) * orig_waveform + blend_ratio * denoised_waveform
output = output / output.abs().max()
# Step 5: Save to file
output_path = "enhanced_output.wav"
torchaudio.save(output_path, output, sr)
return output_path
# Gradio app UI
interface = gr.Interface(
fn=enhance_vo,
inputs=[
gr.Audio(type="filepath", label="Upload MP3 or WAV"),
gr.Slider(0, 100, value=100, label="Noise Reduction Strength (%)")
],
outputs=gr.Audio(type="filepath", label="Enhanced Audio (WAV)"),
title="Adobe-style VO Enhancer (Online Model)",
description="Upload VO audio (MP3/WAV), adjust slider, and download cleaned WAV file."
)
interface.launch()
|