feat: add target-and-remainder stem extraction
This commit is contained in:
Mikei386
@@ -1,15 +1,18 @@
|
||||
# Athena Stem Separator
|
||||
|
||||
Exklusiver dritter Athena-Betriebsmodus für lokale Zwei- bis Sechs-Spur-Trennung.
|
||||
Exklusiver dritter Athena-Betriebsmodus zum gezielten Herauslösen einer Quelle.
|
||||
Der Download enthält immer die Zielspur und eine zweite Spur mit dem kompletten
|
||||
Rest ohne dieses Ziel.
|
||||
|
||||
- Engine: `audio-separator` 0.47.0 (MIT)
|
||||
- **Gesang / Instrumental:** BS-RoFormer Viperx 1297,
|
||||
`model_bs_roformer_ep_317_sdr_12.9755.ckpt`; Vocal SDR 12,9,
|
||||
Instrumental SDR 17,0.
|
||||
- **4 Spuren:** `htdemucs_ft.yaml` mit Gesang, Schlagzeug, Bass und Rest.
|
||||
- **6 Spuren (experimentell):** `htdemucs_6s.yaml` ergänzt gemeinsame Gitarre
|
||||
und Piano. Die Instrumentqualität liegt unter der spezialisierten
|
||||
Zwei-Spur-Trennung.
|
||||
- **Schlagzeug oder Bass:** `htdemucs_ft.yaml`; die nicht gewählten Stems werden
|
||||
zu einer gemeinsamen Restspur summiert.
|
||||
- **Gitarre oder Piano (experimentell):** `htdemucs_6s.yaml`; auch hier werden
|
||||
alle übrigen Stems wieder zur Restspur zusammengesetzt. Die Instrumentqualität
|
||||
liegt unter der spezialisierten Gesangstrennung.
|
||||
- GPU: RTX 5080; LLM, Bildmodelle, TTS und ACE-Step sind dabei verriegelt.
|
||||
- Privat erreichbar: `http://192.168.1.212:8007/`
|
||||
|
||||
@@ -19,5 +22,7 @@ werden nach dem ZIP-Download entfernt. Eigene Spuren für E-/Akustikgitarre,
|
||||
Synthesizer und Streicher sind bewusst noch nicht angeboten: Dafür braucht es
|
||||
weitere Zielmodelle; sie aus `other` umzubenennen wäre fachlich falsch.
|
||||
|
||||
Die API erwartet `multipart/form-data` mit `file` und optional `mode`:
|
||||
`vocals` (Standard), `four_stem` oder `six_stem`.
|
||||
Die API erwartet `multipart/form-data` mit `file` und optional `target`:
|
||||
`vocals` (Standard), `drums`, `bass`, `guitar` oder `piano`. Das ältere Feld
|
||||
`mode` mit `vocals`, `four_stem` oder `six_stem` bleibt für vorhandene Clients
|
||||
erhalten und liefert weiterhin alle Modell-Stems.
|
||||
|
||||
@@ -27,6 +27,13 @@ MODES = {
|
||||
"four_stem": {"model": "htdemucs_ft.yaml", "stems": ("vocals", "drums", "bass", "other"), "archive": "athena-4-stems.zip", "engine": "demucs"},
|
||||
"six_stem": {"model": "htdemucs_6s.yaml", "stems": ("vocals", "drums", "bass", "guitar", "piano", "other"), "archive": "athena-6-stems-experimental.zip", "engine": "demucs"},
|
||||
}
|
||||
TARGETS = {
|
||||
"vocals": {"mode": "vocals", "stem": "vocals", "remainder": "instrumental", "archive": "athena-gesang-und-rest.zip", "rest_file": "instrumental.flac"},
|
||||
"drums": {"mode": "four_stem", "stem": "drums", "archive": "athena-schlagzeug-und-rest.zip", "rest_file": "rest-ohne-schlagzeug.flac"},
|
||||
"bass": {"mode": "four_stem", "stem": "bass", "archive": "athena-bass-und-rest.zip", "rest_file": "rest-ohne-bass.flac"},
|
||||
"guitar": {"mode": "six_stem", "stem": "guitar", "archive": "athena-gitarre-und-rest.zip", "rest_file": "rest-ohne-gitarre.flac"},
|
||||
"piano": {"mode": "six_stem", "stem": "piano", "archive": "athena-piano-und-rest.zip", "rest_file": "rest-ohne-piano.flac"},
|
||||
}
|
||||
|
||||
app = FastAPI(title="Athena Stem Separator", version="2.0")
|
||||
|
||||
@@ -43,6 +50,7 @@ def health() -> dict:
|
||||
"status": "ok" if all(available.values()) else "starting",
|
||||
"models": {name: mode["model"] for name, mode in MODES.items()},
|
||||
"models_ready": available,
|
||||
"targets": list(TARGETS),
|
||||
"busy": SEPARATION_LOCK.locked(),
|
||||
"uptime_seconds": round(time.time() - STARTED, 1),
|
||||
}
|
||||
@@ -80,11 +88,34 @@ def _stem_name(path: Path, expected: tuple[str, ...]) -> str | None:
|
||||
return None
|
||||
|
||||
|
||||
def _mix_remainder(stems: list[Path], output_path: Path) -> None:
|
||||
args = ["ffmpeg", "-hide_banner", "-loglevel", "error", "-y"]
|
||||
for stem in stems:
|
||||
args.extend(["-i", str(stem)])
|
||||
inputs = "".join(f"[{index}:a]" for index in range(len(stems)))
|
||||
args.extend([
|
||||
"-filter_complex", f"{inputs}amix=inputs={len(stems)}:normalize=0:dropout_transition=0[rest]",
|
||||
"-map", "[rest]", "-ar", "44100", "-c:a", "flac", str(output_path),
|
||||
])
|
||||
completed = subprocess.run(args, capture_output=True, text=True, timeout=1800)
|
||||
if completed.returncode:
|
||||
detail = (completed.stderr or completed.stdout or "unknown ffmpeg error")[-4000:]
|
||||
raise RuntimeError(f"Restspur konnte nicht erzeugt werden: {detail}")
|
||||
|
||||
|
||||
@app.post("/v1/separate")
|
||||
async def separate(file: UploadFile = File(...), mode: str = Form("vocals")) -> FileResponse:
|
||||
selected_mode = MODES.get(mode)
|
||||
async def separate(
|
||||
file: UploadFile = File(...),
|
||||
target: str | None = Form(None),
|
||||
mode: str | None = Form(None),
|
||||
) -> FileResponse:
|
||||
selected_target = TARGETS.get(target) if target else None
|
||||
if target and selected_target is None:
|
||||
raise HTTPException(422, f"Unbekannte Zielspur: {target}")
|
||||
selected_mode_name = selected_target["mode"] if selected_target else (mode or "vocals")
|
||||
selected_mode = MODES.get(selected_mode_name)
|
||||
if selected_mode is None:
|
||||
raise HTTPException(422, f"Unbekannter Trennmodus: {mode}")
|
||||
raise HTTPException(422, f"Unbekannter Trennmodus: {selected_mode_name}")
|
||||
suffix = Path(file.filename or "upload.wav").suffix.lower()
|
||||
if suffix not in ALLOWED:
|
||||
raise HTTPException(415, "Dieses Audioformat wird nicht unterstützt.")
|
||||
@@ -114,14 +145,30 @@ async def separate(file: UploadFile = File(...), mode: str = Form("vocals")) ->
|
||||
if missing:
|
||||
found = ", ".join(stem.name for stem in stems) or "keine"
|
||||
raise RuntimeError(f"Fehlende Spuren: {', '.join(missing)}; gefunden: {found}")
|
||||
archive = job / selected_mode["archive"]
|
||||
archive_name = selected_target["archive"] if selected_target else selected_mode["archive"]
|
||||
archive = job / archive_name
|
||||
with zipfile.ZipFile(archive, "w", compression=zipfile.ZIP_STORED) as bundle:
|
||||
for stem in expected:
|
||||
bundle.write(recognized[stem], f"{stem}.flac")
|
||||
if selected_target:
|
||||
target_stem = selected_target["stem"]
|
||||
bundle.write(recognized[target_stem], f"{target_stem}.flac")
|
||||
if "remainder" in selected_target:
|
||||
remainder = recognized[selected_target["remainder"]]
|
||||
else:
|
||||
remainder = job / selected_target["rest_file"]
|
||||
await asyncio.to_thread(
|
||||
_mix_remainder,
|
||||
[recognized[stem] for stem in expected if stem != target_stem],
|
||||
remainder,
|
||||
)
|
||||
bundle.write(remainder, selected_target["rest_file"])
|
||||
else:
|
||||
# Rückwärtskompatibilität für bestehende API-Clients.
|
||||
for stem in expected:
|
||||
bundle.write(recognized[stem], f"{stem}.flac")
|
||||
return FileResponse(
|
||||
archive,
|
||||
media_type="application/zip",
|
||||
filename=selected_mode["archive"],
|
||||
filename=archive_name,
|
||||
background=BackgroundTask(_cleanup, job),
|
||||
)
|
||||
except HTTPException:
|
||||
|
||||
@@ -1,9 +1,15 @@
|
||||
<!doctype html>
|
||||
<html lang="de"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
|
||||
<title>Athena · Spuren 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(820px,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}.modes{display:grid;grid-template-columns:repeat(3,1fr);gap:10px;margin:24px 0}.mode{display:block;border:1px solid var(--line);border-radius:14px;padding:14px;cursor:pointer}.mode:has(input:checked){border-color:var(--cyan);background:#48d7f510}.mode input{display:none}.mode b,.mode span{display:block}.mode span{color:var(--muted);font-size:13px;margin-top:5px;line-height:1.35}.drop{display:block;margin:20px 0;padding:36px 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}.drop 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}@media(max-width:680px){.modes{grid-template-columns:1fr}}
|
||||
</style></head><body><main class="card"><div class="eyebrow">Athena Audio Lab</div><h1>Instrumente und Stimmen trennen</h1><p>Wähle zwischen der besonders sauberen Gesangstrennung und zusammengehörigen Mehrspur-Modellen.</p>
|
||||
<div class="modes"><label class="mode"><input type="radio" name="mode" value="vocals" checked><b>Gesang · beste Qualität</b><span>Vocals + Instrumental<br>BS‑RoFormer</span></label><label class="mode"><input type="radio" name="mode" value="four_stem"><b>4 Spuren</b><span>Gesang, Schlagzeug, Bass, Rest<br>HTDemucs FT</span></label><label class="mode"><input type="radio" name="mode" value="six_stem"><b>6 Spuren · experimentell</b><span>Zusätzlich Gitarre und Piano<br>HTDemucs 6s</span></label></div>
|
||||
<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>Spuren erzeugen</button><div class="status" id="status">Bereit.</div><div class="bar" id="bar"><div class="fill"></div></div><small>Alles läuft lokal auf Athena. Synthesizer, Streicher sowie elektrische und akustische Gitarre separat benötigen zusätzliche Spezialmodelle und sind noch nicht freigeschaltet.</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;const info={vocals:['athena-vocals-instrumental.zip','vocals.flac und instrumental.flac'],four_stem:['athena-4-stems.zip','vier Spuren'],six_stem:['athena-6-stems-experimental.zip','sechs Spuren']};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()=>{const mode=document.querySelector('input[name=mode]:checked').value;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);body.append('mode',mode);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=info[mode][0];a.click();setTimeout(()=>URL.revokeObjectURL(a.href),5000);status.textContent=`Fertig – ZIP mit ${info[mode][1]} wurde geladen.`}catch(e){status.textContent=`Fehler: ${e.message}`}finally{bar.classList.remove('run');start.disabled=false}};
|
||||
<title>Athena · Spuren herauslösen</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(880px,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}.targets{display:grid;grid-template-columns:repeat(5,1fr);gap:9px;margin:24px 0}.target{display:block;border:1px solid var(--line);border-radius:14px;padding:14px 10px;text-align:center;cursor:pointer}.target:has(input:checked){border-color:var(--cyan);background:#48d7f510;box-shadow:0 0 0 1px #48d7f528}.target input{display:none}.target b,.target span{display:block}.target span{color:var(--muted);font-size:12px;margin-top:5px;line-height:1.35}.drop{display:block;margin:20px 0;padding:36px 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}.drop 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}@media(max-width:760px){.targets{grid-template-columns:repeat(2,1fr)}}
|
||||
</style></head><body><main class="card"><div class="eyebrow">Athena Audio Lab</div><h1>Was möchtest du herauslösen?</h1><p>Der Download enthält immer die gewählte Spur separat und zusätzlich den vollständigen Rest ohne diese Spur.</p>
|
||||
<div class="targets">
|
||||
<label class="target"><input type="radio" name="target" value="vocals" checked><b>Gesang</b><span>BS‑RoFormer<br>beste Qualität</span></label>
|
||||
<label class="target"><input type="radio" name="target" value="drums"><b>Schlagzeug</b><span>HTDemucs FT</span></label>
|
||||
<label class="target"><input type="radio" name="target" value="bass"><b>Bass</b><span>HTDemucs FT</span></label>
|
||||
<label class="target"><input type="radio" name="target" value="guitar"><b>Gitarre</b><span>HTDemucs 6s<br>experimentell</span></label>
|
||||
<label class="target"><input type="radio" name="target" value="piano"><b>Piano</b><span>HTDemucs 6s<br>experimentell</span></label>
|
||||
</div>
|
||||
<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>Ausgewählte Spur und Rest erzeugen</button><div class="status" id="status">Bereit.</div><div class="bar" id="bar"><div class="fill"></div></div><small>Alles läuft lokal auf Athena. Synthesizer, Streicher sowie elektrische und akustische Gitarre separat benötigen zusätzliche Spezialmodelle.</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;const names={vocals:'gesang',drums:'schlagzeug',bass:'bass',guitar:'gitarre',piano:'piano'};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()=>{const target=document.querySelector('input[name=target]:checked').value;start.disabled=true;bar.classList.add('run');status.textContent='Modell löst die gewählte Spur heraus – das kann einige Minuten dauern …';let body=new FormData();body.append('file',selected);body.append('target',target);try{let r=await fetch('/v1/separate',{method:'POST',body});if(!r.ok)throw Error((await r.json()).detail||`HTTP ${r.status}`);let blob=await r.blob(),a=document.createElement('a');a.href=URL.createObjectURL(blob);a.download=`athena-${names[target]}-und-rest.zip`;a.click();setTimeout(()=>URL.revokeObjectURL(a.href),5000);status.textContent='Fertig – ZIP mit der ausgewählten Spur und dem Rest 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