Upload 2 files

app.py

@@ -1,34 +1,43 @@
+
 import gradio as gr
+import requests
+import soundfile as sf
+import io
+import torch
 import torchaudio
-from speechbrain.inference.enhance import Denoise
 
-# Load new model (this one works with SpeechBrain 1.0+)
-denoiser = Denoise.from_hparams(
-    source="speechbrain/denoise",
-    savedir="denoise_model"
-)
+API_URL = "https://hf.space/embed/akhaliq/denoise-audio/+/api/predict"
 
 def enhance_vo(file, denoise_strength):
-    # Load original audio
-    orig, fs = torchaudio.load(file)
+    # Step 1: Read audio and send to remote model
+    with open(file, "rb") as f:
+        response = requests.post(API_URL, files={"data": f})
 
-    # Denoise audio
-    cleaned = denoiser.enhance(orig, fs)
+    if response.status_code != 200:
+        raise Exception("Denoising model failed to process audio.")
 
-    # Blend original and cleaned based on slider value (dry/wet mix)
-    blend_ratio = denoise_strength / 100.0
-    output = (1 - blend_ratio) * orig + blend_ratio * cleaned
+    # 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)
 
-    # Normalize to avoid clipping
+    # 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()
 
-    # Save output
+    # Step 5: Save to file
     output_path = "enhanced_output.wav"
-    torchaudio.save(output_path, output, fs)
+    torchaudio.save(output_path, output, sr)
 
     return output_path
 
-# Gradio app
+# Gradio app UI
 interface = gr.Interface(
     fn=enhance_vo,
     inputs=[
@@ -36,8 +45,8 @@ interface = gr.Interface(
         gr.Slider(0, 100, value=100, label="Noise Reduction Strength (%)")
     ],
     outputs=gr.Audio(type="filepath", label="Enhanced Audio (WAV)"),
-    title="VO Audio Enhancer",
-    description="Upload your voiceover (MP3/WAV), adjust the noise reduction level, and download the enhanced file."
+    title="Adobe-style VO Enhancer (Online Model)",
+    description="Upload VO audio (MP3/WAV), adjust slider, and download cleaned WAV file."
 )
 
 interface.launch()

requirements.txt

@@ -1,3 +1,5 @@
+
 gradio
+requests
 torchaudio
-speechbrain>=1.0.0
+soundfile