Spaces:
Running
Running
| import os | |
| import shutil | |
| import subprocess | |
| import tempfile | |
| from pathlib import Path | |
| import gradio as gr | |
| import torchaudio | |
| import torch | |
| import soundfile as sf | |
| # ================================ | |
| # CONFIG | |
| # ================================ | |
| DEVICE = "cuda" if torch.cuda.is_available() else "cpu" | |
| MODEL = "htdemucs" # best quality vocal separation | |
| def resave(src, dst): | |
| wav, sr = torchaudio.load(str(src)) | |
| data = wav.numpy().T | |
| sf.write(dst, data, sr) | |
| # ================================ | |
| # SPLIT FUNCTION | |
| # ================================ | |
| def split_vocals(audio_file): | |
| if audio_file is None: | |
| return None, None, "❌ Please upload an audio file." | |
| work_dir = tempfile.mkdtemp(prefix="demucs_") | |
| try: | |
| print(f"[Demucs] Input: {audio_file}") | |
| print(f"[Demucs] Device: {DEVICE}") | |
| # Run Demucs | |
| result = subprocess.run( | |
| [ | |
| "python", "-m", "demucs", | |
| "--two-stems", "vocals", # only split vocals vs everything else | |
| "-n", MODEL, | |
| "-o", work_dir, | |
| audio_file, | |
| ], | |
| capture_output=True, | |
| text=True, | |
| ) | |
| if result.returncode != 0: | |
| error = result.stderr[-1000:] # last 1000 chars to avoid huge dumps | |
| print(f"[Demucs] Error:\n{error}") | |
| return None, None, f"❌ Demucs failed:\n{error}" | |
| # Find output files | |
| track_name = Path(audio_file).stem | |
| demucs_out = Path(work_dir) / MODEL / track_name | |
| vocals_src = demucs_out / "vocals.wav" | |
| background_src = demucs_out / "no_vocals.wav" | |
| if not vocals_src.exists() or not background_src.exists(): | |
| return None, None, "❌ Demucs ran but output files not found." | |
| # Copy to stable paths | |
| vocals_dst = str(Path(work_dir) / "vocals.wav") | |
| background_dst = str(Path(work_dir) / "background.wav") | |
| resave(vocals_src, vocals_dst) | |
| resave(background_src, background_dst) | |
| print(f"[Demucs] ✅ Done. Vocals: {vocals_dst}") | |
| return vocals_dst, background_dst, "✅ Split complete!" | |
| except Exception as e: | |
| return None, None, f"❌ Exception: {str(e)}" | |
| # ================================ | |
| # GRADIO UI | |
| # ================================ | |
| with gr.Blocks(title="CleanSong AI — Demucs Splitter") as demo: | |
| gr.Markdown("# 🎸 CleanSong AI — Vocal Splitter") | |
| gr.Markdown( | |
| "Upload a song → get the isolated **vocals** and **background** tracks back separately. " | |
| "Powered by Demucs `htdemucs` model." | |
| ) | |
| with gr.Row(): | |
| with gr.Column(): | |
| audio_input = gr.Audio( | |
| label="Upload Song", | |
| type="filepath", | |
| sources=["upload"], | |
| ) | |
| split_btn = gr.Button("🎸 Split Vocals", variant="primary", size="lg") | |
| with gr.Column(): | |
| status = gr.Textbox(label="Status", interactive=False) | |
| vocals_out = gr.Audio(label="Vocals Only", type="filepath") | |
| background_out = gr.Audio(label="Background / Instrumental", type="filepath") | |
| split_btn.click( | |
| fn=split_vocals, | |
| inputs=[audio_input], | |
| outputs=[vocals_out, background_out, status], | |
| ) | |
| gr.Markdown( | |
| """ | |
| --- | |
| **Part of the CleanSong AI pipeline.** | |
| - Upload your song here first to get isolated vocals | |
| - Feed the vocals into the Whisper Transcriber Space | |
| - The background track is kept intact for the final remix | |
| """ | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() | |