Mikei386
6db10fbc3f
Fügt einen OpenAI-kompatiblen TTS-Endpunkt POST /v1/audio/speech hinzu. Die Synthese läuft in einem separaten, langlebigen Worker (mike-ai-kokoro.service) mit eigenem Venv (CPU-only torch) und hält die Modelle dauerhaft im RAM (niedrige Warm-Start-Latenz). - Zwei deutsche Stimmen: kikiri-german-martin, kikiri-german-victoria (Apache 2.0, je ~327 MB) unter /opt/mike-ai/models/kokoro/ - Deutsche G2P über espeak-ng (phonemizer), kein spacy/thinc 9.x nötig (kokoro mit --no-deps + misaki ohne [en], Python 3.13-kompatibel) - Formate: mp3 (Default), wav, flac, pcm; speed 0.5-2.0 - /status um tts.*-Felder erweitert (reachable, ready, voices, ...) - TTS ohne GPU-Lock: blockiert weder Qwen/llama.cpp noch FLUX - systemd-Unit mike-ai-kokoro.service (Start beim Boot) - install.sh/deploy.sh um Kokoro-Venv + Modell-Download erweitert - Mock-TTS-Worker + 11 TTS-Tests (insgesamt 43, alle bestanden) - Hörproben (je ~40 s) + Benchmark (RTF ~0.23, ~4.3x Echtzeit) Kein Push – erst nach User-Freigabe.
317 lines
11 KiB
Python
317 lines
11 KiB
Python
#!/usr/bin/env python3
|
||
"""Kokoro TTS Worker – langlebiger HTTP-Service für deutsche Sprachausgabe.
|
||
|
||
Lädt die Kokoro-82M-Feintuning-Modelle (kikiri-german-martin,
|
||
kikiri-german-victoria) einmalig beim Start und hält sie dauerhaft im
|
||
RAM (CPU-only, niedrige Warm-Start-Latenz). Wird als eigener
|
||
systemd-Service betrieben und vom AI Profile Router über HTTP
|
||
angesprochen (POST /v1/audio/speech -> POST /tts).
|
||
|
||
API:
|
||
GET /status -> {"status":"ok","ready":bool,"voices":[...],...}
|
||
POST /tts -> {"text":"...","voice":"martin","speed":1.0,
|
||
"format":"wav|mp3|flac|pcm"} -> binäres Audio
|
||
|
||
Logging nach stderr (journald). stdout bleibt frei.
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import logging
|
||
import os
|
||
import sys
|
||
import threading
|
||
import time
|
||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Konfiguration (über Umgebungsvariablen, vgl. systemd-Unit)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
HOST = os.environ.get("KOKORO_HOST", "127.0.0.1")
|
||
PORT = int(os.environ.get("KOKORO_PORT", "8082"))
|
||
MODEL_DIR = os.environ.get("KOKORO_MODEL_DIR", "/opt/mike-ai/models/kokoro")
|
||
|
||
# Stimmen: Name -> Pfade relativ zu MODEL_DIR.
|
||
# Beide Modelle sind eigenständige Kokoro-82M-Feintunings (Apache 2.0).
|
||
VOICES = {
|
||
"martin": {
|
||
"config": "kikiri-german-martin/config.json",
|
||
"model": "kikiri-german-martin/kikiri_german_martin_ep10.pth",
|
||
"voice": "kikiri-german-martin/voices/martin.pt",
|
||
},
|
||
"victoria": {
|
||
"config": "kikiri-german-victoria/config.json",
|
||
"model": "kikiri-german-victoria/kikiri_german_victoria_ep10.pth",
|
||
"voice": "kikiri-german-victoria/voices/victoria.pt",
|
||
},
|
||
}
|
||
DEFAULT_VOICE = "martin"
|
||
SAMPLE_RATE = 24000 # Kokoro-nativ
|
||
SPEED_MIN, SPEED_MAX = 0.5, 2.0
|
||
MAX_TEXT_LEN = 8000 # Zeichen pro Request
|
||
|
||
log = logging.getLogger("kokoro-tts")
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Worker
|
||
# ---------------------------------------------------------------------------
|
||
|
||
class TTSWorker:
|
||
"""Hält die geladenen Pipelines und serialisiert die Synthese."""
|
||
|
||
def __init__(self) -> None:
|
||
self.pipelines: dict[str, tuple] = {} # name -> (KPipeline, voice)
|
||
self.load_errors: list[str] = []
|
||
self.ready = False
|
||
self.started = time.time()
|
||
self._lock = threading.Lock()
|
||
self.last_seconds: float | None = None
|
||
self.last_voice: str | None = None
|
||
self.last_error: str | None = None
|
||
self.total_requests = 0
|
||
|
||
def load(self) -> None:
|
||
"""Lädt alle Stimmen (CPU-only)."""
|
||
import torch
|
||
from kokoro import KModel, KPipeline
|
||
# Deutsche Sprachunterstützung (kokoro PR #340): 'de' -> espeak-ng G2P.
|
||
from kokoro import pipeline as _pipeline_mod
|
||
_pipeline_mod.ALIASES.setdefault("de", "d")
|
||
_pipeline_mod.LANG_CODES.setdefault("d", "de")
|
||
|
||
for name, cfg in VOICES.items():
|
||
t0 = time.monotonic()
|
||
try:
|
||
kmodel = KModel(
|
||
config=os.path.join(MODEL_DIR, cfg["config"]),
|
||
model=os.path.join(MODEL_DIR, cfg["model"]),
|
||
).to("cpu").eval()
|
||
pipeline = KPipeline(lang_code="de", model=kmodel)
|
||
voice = torch.load(
|
||
os.path.join(MODEL_DIR, cfg["voice"]),
|
||
map_location="cpu", weights_only=True)
|
||
self.pipelines[name] = (pipeline, voice)
|
||
log.info("Stimme geladen: %s (%.1f s)", name,
|
||
time.monotonic() - t0)
|
||
except Exception as e:
|
||
self.load_errors.append(f"{name}: {e}")
|
||
log.error("Stimme %s nicht ladbar: %s", name, e)
|
||
self.ready = True
|
||
|
||
def synthesize(self, text: str, voice: str, speed: float) -> bytes:
|
||
"""Synthetisiert Audio und liefert es als WAV-Bytes (24 kHz)."""
|
||
with self._lock:
|
||
if voice not in self.pipelines:
|
||
raise ValueError(f"unbekannte Stimme: {voice!r} "
|
||
f"(erlaubt: {', '.join(VOICES)})")
|
||
pipeline, voice_pack = self.pipelines[voice]
|
||
t0 = time.monotonic()
|
||
chunks = list(pipeline(text, voice=voice_pack, speed=speed))
|
||
audios = [c[2] for c in chunks if c[2] is not None]
|
||
if not audios:
|
||
raise RuntimeError("keine Audio-Daten erzeugt")
|
||
import torch
|
||
audio = torch.cat(audios, dim=0)
|
||
seconds = time.monotonic() - t0
|
||
self.last_seconds = seconds
|
||
self.last_voice = voice
|
||
self.total_requests += 1
|
||
return _to_wav_bytes(audio)
|
||
|
||
|
||
def _to_wav_bytes(audio) -> bytes:
|
||
"""1D-Tensor (24 kHz) -> WAV-Bytes (16-bit PCM)."""
|
||
import io
|
||
import numpy as np
|
||
import soundfile as sf
|
||
arr = audio.detach().cpu().numpy().astype("float32")
|
||
buf = io.BytesIO()
|
||
sf.write(buf, arr, SAMPLE_RATE, format="WAV", subtype="PCM_16")
|
||
return buf.getvalue()
|
||
|
||
|
||
def _wav_to_format(wav_bytes: bytes, fmt: str) -> bytes:
|
||
"""WAV-Bytes in das Zielformat konvertieren."""
|
||
if fmt == "wav":
|
||
return wav_bytes
|
||
import io
|
||
import numpy as np
|
||
import soundfile as sf
|
||
data, sr = sf.read(io.BytesIO(wav_bytes), dtype="float32")
|
||
if fmt == "flac":
|
||
buf = io.BytesIO()
|
||
sf.write(buf, data, sr, format="FLAC")
|
||
return buf.getvalue()
|
||
if fmt == "pcm":
|
||
# 16-bit PCM, little-endian, mono
|
||
pcm = (np.clip(data, -1.0, 1.0) * 32767).astype("<i2")
|
||
return pcm.tobytes()
|
||
if fmt == "mp3":
|
||
import lameenc
|
||
pcm = (np.clip(data, -1.0, 1.0) * 32767).astype("<i2")
|
||
encoder = lameenc.Encoder()
|
||
encoder.set_bit_rate(128)
|
||
encoder.set_in_sample_rate(sr)
|
||
encoder.set_channels(1)
|
||
mp3 = encoder.encode(pcm.tobytes())
|
||
mp3 += encoder.flush()
|
||
return mp3
|
||
raise ValueError(f"unbekanntes Format: {fmt!r}")
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# HTTP-Handler
|
||
# ---------------------------------------------------------------------------
|
||
|
||
WORKER = TTSWorker()
|
||
|
||
|
||
class Handler(BaseHTTPRequestHandler):
|
||
server_version = "KokoroTTS/1.0"
|
||
timeout = 300 # s, Synthese kann dauern
|
||
|
||
def log_message(self, fmt, *args): # noqa: N802
|
||
log.info("%s %s", self.address_string(), fmt % args)
|
||
|
||
def do_GET(self): # noqa: N802
|
||
if self.path.split("?", 1)[0] == "/status":
|
||
self._send_json(200, self._status_payload())
|
||
else:
|
||
self._send_json(404, {"error": "not found"})
|
||
|
||
def do_POST(self): # noqa: N802
|
||
if self.path.split("?", 1)[0] == "/tts":
|
||
self._tts()
|
||
else:
|
||
self._send_json(404, {"error": "not found"})
|
||
|
||
def _status_payload(self) -> dict:
|
||
return {
|
||
"status": "ok",
|
||
"ready": WORKER.ready,
|
||
"voices": list(VOICES),
|
||
"default_voice": DEFAULT_VOICE,
|
||
"load_errors": WORKER.load_errors,
|
||
"sample_rate": SAMPLE_RATE,
|
||
"uptime_seconds": round(time.time() - WORKER.started, 1),
|
||
"total_requests": WORKER.total_requests,
|
||
"last_seconds": WORKER.last_seconds,
|
||
"last_voice": WORKER.last_voice,
|
||
"last_error": WORKER.last_error,
|
||
}
|
||
|
||
def _tts(self) -> None:
|
||
length = int(self.headers.get("Content-Length") or 0)
|
||
try:
|
||
data = json.loads(self.rfile.read(length))
|
||
except ValueError:
|
||
self._send_json(400, {"error": "ungültiges JSON"})
|
||
return
|
||
if not isinstance(data, dict):
|
||
self._send_json(400, {"error": "Request muss ein JSON-Objekt sein"})
|
||
return
|
||
|
||
text = data.get("text")
|
||
if not isinstance(text, str) or not text.strip():
|
||
self._send_json(400, {"error": "'text' fehlt oder ist leer"})
|
||
return
|
||
if len(text) > MAX_TEXT_LEN:
|
||
self._send_json(400, {"error": f"'text' zu lang (max {MAX_TEXT_LEN})"})
|
||
return
|
||
|
||
voice = data.get("voice", DEFAULT_VOICE)
|
||
if voice not in VOICES:
|
||
self._send_json(400, {"error": f"unbekannte Stimme: {voice!r}"})
|
||
return
|
||
|
||
speed = data.get("speed", 1.0)
|
||
try:
|
||
speed = float(speed)
|
||
except (TypeError, ValueError):
|
||
self._send_json(400, {"error": "'speed' muss eine Zahl sein"})
|
||
return
|
||
if not SPEED_MIN <= speed <= SPEED_MAX:
|
||
self._send_json(400, {"error": f"'speed' muss zwischen "
|
||
f"{SPEED_MIN} und {SPEED_MAX} sein"})
|
||
return
|
||
|
||
fmt = data.get("format", "wav")
|
||
if fmt not in ("wav", "mp3", "flac", "pcm"):
|
||
self._send_json(400, {"error": f"ungültiges Format: {fmt!r}"})
|
||
return
|
||
|
||
if not WORKER.ready:
|
||
self._send_json(503, {"error": "TTS-Worker lädt noch"})
|
||
return
|
||
if not WORKER.pipelines:
|
||
self._send_json(503, {"error": "keine Stimme geladen",
|
||
"load_errors": WORKER.load_errors})
|
||
return
|
||
|
||
try:
|
||
wav = WORKER.synthesize(text.strip(), voice, speed)
|
||
audio = _wav_to_format(wav, fmt)
|
||
except (ValueError, RuntimeError) as e:
|
||
WORKER.last_error = str(e)
|
||
self._send_json(500, {"error": str(e)})
|
||
return
|
||
|
||
content_type = {
|
||
"wav": "audio/wav",
|
||
"mp3": "audio/mpeg",
|
||
"flac": "audio/flac",
|
||
"pcm": "application/octet-stream",
|
||
}[fmt]
|
||
self._send_bytes(200, audio, content_type)
|
||
|
||
def _send_json(self, code: int, payload: dict) -> None:
|
||
body = json.dumps(payload, ensure_ascii=False).encode()
|
||
self.send_response(code)
|
||
self.send_header("Content-Type", "application/json")
|
||
self.send_header("Content-Length", str(len(body)))
|
||
self.send_header("Connection", "close")
|
||
self.end_headers()
|
||
self.wfile.write(body)
|
||
|
||
def _send_bytes(self, code: int, data: bytes, content_type: str) -> None:
|
||
self.send_response(code)
|
||
self.send_header("Content-Type", content_type)
|
||
self.send_header("Content-Length", str(len(data)))
|
||
self.send_header("Connection", "close")
|
||
self.end_headers()
|
||
self.wfile.write(data)
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Main
|
||
# ---------------------------------------------------------------------------
|
||
|
||
def main() -> None:
|
||
logging.basicConfig(
|
||
level=os.environ.get("LOG_LEVEL", "INFO"),
|
||
format="%(asctime)s %(levelname)s %(message)s",
|
||
stream=sys.stderr,
|
||
)
|
||
log.info("Kokoro TTS Worker startet: %s:%s (Modelle: %s)",
|
||
HOST, PORT, ", ".join(VOICES))
|
||
WORKER.load()
|
||
if not WORKER.pipelines:
|
||
log.error("Keine Stimme geladen – Worker bleibt trotzdem erreichbar "
|
||
"(/status zeigt load_errors)")
|
||
server = ThreadingHTTPServer((HOST, PORT), Handler)
|
||
server.daemon_threads = True
|
||
log.info("Kokoro TTS Worker bereit (%d Stimmen)", len(WORKER.pipelines))
|
||
try:
|
||
server.serve_forever()
|
||
except KeyboardInterrupt:
|
||
pass
|
||
finally:
|
||
server.server_close()
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|