Add BS-RoFormer vocal separation mode
This commit is contained in:
Mikei386 committed
1 parent
a4e894fe70
commit
0069b61dbb
15 files changed
+421
-52
No files matched your search
@@ -0,0 +1,22 @@
|
||||
FROM pytorch/pytorch:2.7.1-cuda12.8-cudnn9-runtime@sha256:c16f4c749e2d9e96878875cdf6cc45cddda1d1a36fddd371dd6f2360f1b6e2a2
|
||||
|
||||
RUN apt-get update \
|
||||
&& DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends build-essential curl ffmpeg libsndfile1 \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
RUN python -m pip install --no-cache-dir \
|
||||
"audio-separator[gpu]==0.47.0" \
|
||||
"onnxruntime-gpu==1.22.0" \
|
||||
"fastapi==0.116.1" \
|
||||
"python-multipart==0.0.20" \
|
||||
"uvicorn[standard]==0.35.0"
|
||||
|
||||
WORKDIR /app
|
||||
COPY app.py index.html ./
|
||||
|
||||
ENV MODEL_FILENAME=model_bs_roformer_ep_317_sdr_12.9755.ckpt \
|
||||
MODEL_DIR=/models \
|
||||
JOB_DIR=/data/jobs
|
||||
|
||||
EXPOSE 8080
|
||||
CMD ["sh", "-c", "audio-separator --model_filename \"$MODEL_FILENAME\" --model_file_dir \"$MODEL_DIR\" --download_model_only && exec uvicorn app:app --host 0.0.0.0 --port 8080 --workers 1"]
|
||||
@@ -0,0 +1,16 @@
|
||||
# Athena Vocal Separator
|
||||
|
||||
Exklusiver dritter Athena-Betriebsmodus für lokale Zwei-Spur-Trennung in
|
||||
`vocals.flac` und `instrumental.flac`.
|
||||
|
||||
- Engine: `audio-separator` 0.47.0 (MIT)
|
||||
- Modell: BS-RoFormer Viperx 1297,
|
||||
`model_bs_roformer_ep_317_sdr_12.9755.ckpt`
|
||||
- Modellbewertung im audio-separator-Katalog: Vocal SDR 12,9,
|
||||
Instrumental SDR 17,0
|
||||
- GPU: RTX 5080; LLM, Bildmodelle, TTS und ACE-Step sind dabei verriegelt.
|
||||
- Privat erreichbar: `http://192.168.1.212:8007/`
|
||||
|
||||
Das Modell wird beim ersten Start nach `/data/models/audio-separator`
|
||||
heruntergeladen. Temporäre Jobs liegen unter `/data/audio/separation` und
|
||||
werden nach dem ZIP-Download entfernt.
|
||||
@@ -0,0 +1,124 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
import time
|
||||
import zipfile
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import FastAPI, File, HTTPException, UploadFile
|
||||
from fastapi.responses import FileResponse, HTMLResponse
|
||||
from starlette.background import BackgroundTask
|
||||
|
||||
|
||||
MODEL = os.getenv("MODEL_FILENAME", "model_bs_roformer_ep_317_sdr_12.9755.ckpt")
|
||||
MODEL_DIR = Path(os.getenv("MODEL_DIR", "/models"))
|
||||
JOB_DIR = Path(os.getenv("JOB_DIR", "/data/jobs"))
|
||||
MAX_UPLOAD = int(os.getenv("MAX_UPLOAD_BYTES", str(1024 ** 3)))
|
||||
ALLOWED = {".wav", ".flac", ".mp3", ".m4a", ".aac", ".ogg", ".opus", ".wma"}
|
||||
SEPARATION_LOCK = asyncio.Lock()
|
||||
STARTED = time.time()
|
||||
|
||||
app = FastAPI(title="Athena Vocal Separator", version="1.0")
|
||||
|
||||
|
||||
@app.get("/", response_class=HTMLResponse)
|
||||
def index() -> str:
|
||||
return Path("/app/index.html").read_text(encoding="utf-8")
|
||||
|
||||
|
||||
@app.get("/health")
|
||||
def health() -> dict:
|
||||
checkpoint = MODEL_DIR / MODEL
|
||||
return {
|
||||
"status": "ok" if checkpoint.exists() else "starting",
|
||||
"model": MODEL,
|
||||
"model_ready": checkpoint.exists(),
|
||||
"busy": SEPARATION_LOCK.locked(),
|
||||
"uptime_seconds": round(time.time() - STARTED, 1),
|
||||
}
|
||||
|
||||
|
||||
def _cleanup(path: Path) -> None:
|
||||
shutil.rmtree(path, ignore_errors=True)
|
||||
|
||||
|
||||
def _run_separator(input_path: Path, output_dir: Path) -> None:
|
||||
args = [
|
||||
"audio-separator", str(input_path),
|
||||
"--model_filename", MODEL,
|
||||
"--model_file_dir", str(MODEL_DIR),
|
||||
"--output_dir", str(output_dir),
|
||||
"--output_format", "FLAC",
|
||||
"--sample_rate", "44100",
|
||||
"--use_soundfile",
|
||||
"--use_autocast",
|
||||
"--mdxc_segment_size", "256",
|
||||
"--mdxc_overlap", "8",
|
||||
"--mdxc_batch_size", "1",
|
||||
]
|
||||
completed = subprocess.run(args, capture_output=True, text=True, timeout=7200)
|
||||
if completed.returncode:
|
||||
detail = (completed.stderr or completed.stdout or "unknown error")[-4000:]
|
||||
raise RuntimeError(detail)
|
||||
|
||||
|
||||
@app.post("/v1/separate")
|
||||
async def separate(file: UploadFile = File(...)) -> FileResponse:
|
||||
suffix = Path(file.filename or "upload.wav").suffix.lower()
|
||||
if suffix not in ALLOWED:
|
||||
raise HTTPException(415, "Dieses Audioformat wird nicht unterstützt.")
|
||||
if SEPARATION_LOCK.locked():
|
||||
raise HTTPException(409, "Eine Trennung läuft bereits.")
|
||||
|
||||
job = Path(tempfile.mkdtemp(prefix="separate-", dir=JOB_DIR))
|
||||
input_path = job / f"input{suffix}"
|
||||
output_dir = job / "output"
|
||||
output_dir.mkdir()
|
||||
size = 0
|
||||
try:
|
||||
with input_path.open("wb") as handle:
|
||||
while chunk := await file.read(1024 * 1024):
|
||||
size += len(chunk)
|
||||
if size > MAX_UPLOAD:
|
||||
raise HTTPException(413, "Datei ist größer als 1 GiB.")
|
||||
handle.write(chunk)
|
||||
async with SEPARATION_LOCK:
|
||||
await asyncio.to_thread(_run_separator, input_path, output_dir)
|
||||
|
||||
stems = sorted(output_dir.glob("*.flac"))
|
||||
if len(stems) != 2:
|
||||
raise RuntimeError(f"Erwartet wurden zwei FLAC-Dateien, gefunden: {len(stems)}")
|
||||
archive = job / "athena-vocals-instrumental.zip"
|
||||
with zipfile.ZipFile(archive, "w", compression=zipfile.ZIP_STORED) as bundle:
|
||||
for stem in stems:
|
||||
lower = stem.name.lower()
|
||||
target = "vocals.flac" if "vocal" in lower else "instrumental.flac"
|
||||
bundle.write(stem, target)
|
||||
return FileResponse(
|
||||
archive,
|
||||
media_type="application/zip",
|
||||
filename="athena-vocals-instrumental.zip",
|
||||
background=BackgroundTask(_cleanup, job),
|
||||
)
|
||||
except HTTPException:
|
||||
_cleanup(job)
|
||||
raise
|
||||
except subprocess.TimeoutExpired:
|
||||
_cleanup(job)
|
||||
raise HTTPException(504, "Die Trennung hat das Zeitlimit überschritten.")
|
||||
except Exception as exc:
|
||||
_cleanup(job)
|
||||
raise HTTPException(500, f"Trennung fehlgeschlagen: {exc}")
|
||||
|
||||
|
||||
@app.on_event("startup")
|
||||
def prepare() -> None:
|
||||
JOB_DIR.mkdir(parents=True, exist_ok=True)
|
||||
MODEL_DIR.mkdir(parents=True, exist_ok=True)
|
||||
for old in JOB_DIR.glob("separate-*"):
|
||||
if old.is_dir() and time.time() - old.stat().st_mtime > 86400:
|
||||
_cleanup(old)
|
||||
@@ -0,0 +1,38 @@
|
||||
services:
|
||||
stem-separator:
|
||||
build: .
|
||||
image: mike-ai/bs-roformer-separator:0.47.0
|
||||
container_name: mike-ai-stem-separator
|
||||
labels:
|
||||
com.mike-ai.stem-separator: "bs-roformer"
|
||||
environment:
|
||||
NVIDIA_VISIBLE_DEVICES: ${SEPARATOR_GPU_UUID:?set SEPARATOR_GPU_UUID to the RTX 5080 UUID}
|
||||
MODEL_FILENAME: model_bs_roformer_ep_317_sdr_12.9755.ckpt
|
||||
MODEL_DIR: /models
|
||||
JOB_DIR: /data/jobs
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
device_ids: ["${SEPARATOR_GPU_UUID:?set SEPARATOR_GPU_UUID to the RTX 5080 UUID}"]
|
||||
capabilities: [gpu]
|
||||
ports:
|
||||
- "127.0.0.1:${SEPARATOR_PORT:-8007}:8080"
|
||||
volumes:
|
||||
- ${SEPARATOR_MODEL_DIR:-/data/models/audio-separator}:/models
|
||||
- ${SEPARATOR_DATA_DIR:-/data/audio/separation}:/data
|
||||
shm_size: "2gb"
|
||||
restart: "no"
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "curl -fsS http://127.0.0.1:8080/health | grep -q '\"status\":\"ok\"'"]
|
||||
interval: 15s
|
||||
timeout: 5s
|
||||
start_period: 600s
|
||||
retries: 3
|
||||
networks: [frontend]
|
||||
|
||||
networks:
|
||||
frontend:
|
||||
external: true
|
||||
name: mike-ai_frontend
|
||||
@@ -0,0 +1,4 @@
|
||||
<!doctype html><html lang="de"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><title>Athena · Stimmen trennen</title><style>
|
||||
:root{color-scheme:dark;--bg:#07111c;--card:#101d2b;--line:#26384b;--cyan:#48d7f5;--mint:#63e6be;--text:#ecf5ff;--muted:#91a4b7}*{box-sizing:border-box}body{margin:0;background:radial-gradient(circle at 20% 0,#142a42 0,#07111c 42%);font:16px system-ui,sans-serif;color:var(--text);min-height:100vh;display:grid;place-items:center;padding:24px}.card{width:min(760px,100%);padding:32px;border:1px solid var(--line);border-radius:22px;background:rgba(16,29,43,.96);box-shadow:0 25px 70px #0008}.eyebrow{color:var(--cyan);font-weight:800;letter-spacing:.14em;text-transform:uppercase;font-size:12px}h1{font-size:clamp(30px,5vw,52px);margin:.3em 0 .15em}p{color:var(--muted);line-height:1.6}.drop{display:block;margin:28px 0;padding:44px 24px;border:2px dashed #3f5a72;border-radius:18px;text-align:center;cursor:pointer;transition:.2s}.drop:hover,.drop.drag{border-color:var(--cyan);background:#48d7f50b}input{display:none}.file{color:var(--mint);font-weight:700;margin-top:8px}button{width:100%;border:0;border-radius:13px;padding:15px;font-weight:800;font-size:16px;background:linear-gradient(90deg,var(--cyan),var(--mint));color:#05202a;cursor:pointer}button:disabled{opacity:.45;cursor:not-allowed}.status{min-height:28px;margin-top:18px;color:var(--muted)}.bar{height:7px;background:#07111c;border-radius:9px;overflow:hidden;margin-top:12px}.fill{height:100%;width:0;background:linear-gradient(90deg,var(--cyan),var(--mint));transition:.4s}.run .fill{width:85%;animation:pulse 1.5s infinite alternate}@keyframes pulse{to{opacity:.45}}small{display:block;color:#71879a;margin-top:20px}</style></head><body><main class="card"><div class="eyebrow">Athena Audio Lab</div><h1>Stimmen sauber trennen</h1><p>BS‑RoFormer Viperx 1297 zerlegt deinen Titel in zwei verlustfreie FLAC-Spuren: Gesang und Instrumental.</p><label class="drop" id="drop">Audio auswählen oder hier ablegen<input id="file" type="file" accept="audio/*"><div class="file" id="name">Noch keine Datei gewählt</div></label><button id="start" disabled>Vocals und Instrumental erzeugen</button><div class="status" id="status">Bereit.</div><div class="bar" id="bar"><div class="fill"></div></div><small>Die Verarbeitung läuft lokal auf Athena. Nichts wird in eine Cloud hochgeladen.</small></main><script>
|
||||
const file=document.querySelector('#file'),drop=document.querySelector('#drop'),name=document.querySelector('#name'),start=document.querySelector('#start'),status=document.querySelector('#status'),bar=document.querySelector('#bar');let selected;function choose(f){selected=f;name.textContent=f?`${f.name} · ${(f.size/1048576).toFixed(1)} MiB`:'Noch keine Datei gewählt';start.disabled=!f}file.onchange=()=>choose(file.files[0]);drop.ondragover=e=>{e.preventDefault();drop.classList.add('drag')};drop.ondragleave=()=>drop.classList.remove('drag');drop.ondrop=e=>{e.preventDefault();drop.classList.remove('drag');choose(e.dataTransfer.files[0])};start.onclick=async()=>{start.disabled=true;bar.classList.add('run');status.textContent='Modell trennt den Titel – das kann einige Minuten dauern …';let body=new FormData();body.append('file',selected);try{let r=await fetch('/v1/separate',{method:'POST',body});if(!r.ok)throw Error((await r.json()).detail||`HTTP ${r.status}`);let blob=await r.blob(),a=document.createElement('a');a.href=URL.createObjectURL(blob);a.download='athena-vocals-instrumental.zip';a.click();setTimeout(()=>URL.revokeObjectURL(a.href),5000);status.textContent='Fertig – ZIP mit vocals.flac und instrumental.flac wurde geladen.'}catch(e){status.textContent=`Fehler: ${e.message}`}finally{bar.classList.remove('run');start.disabled=false}};
|
||||
</script></body></html>
|
||||
Reference in new issue
Block a user