6a138eff3a
Adds a MeloTTS backend that runs the model in its own melo311 interpreter as a long-lived worker (melo_worker.py), loaded once and fed synthesis requests over a stdin/stdout JSON protocol. fd1 is split from fd2 in the worker so MeloTTS's stdout progress chatter can't corrupt the protocol. Each speak() writes a wav and hands the path to a pluggable sink (the Discord voice step will swap in "play into the call"). factory wires tts=melo; pipeline.aclose now also tears down the tts worker. Verified (CPU): model load ~7.9s once, then a short reply synthesizes in ~0.86s (within the ~1s budget); wav is valid 44.1kHz PCM. GPU (cuda) is selectable via WSAI_MELO_DEVICE for lower latency, pending GPU approval. 7 smoke tests still pass. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
73 lines
2.6 KiB
Python
73 lines
2.6 KiB
Python
"""Persistent MeloTTS worker (Korean).
|
|
|
|
MeloTTS lives in its own Python (melo311); loading the model takes seconds, so
|
|
we load it ONCE here and then serve synthesis requests over stdin/stdout. This
|
|
process is launched with the melo311 interpreter by wsai.backends.melo.MeloTTS.
|
|
|
|
MeloTTS (and its deps) print progress straight to stdout, which would corrupt
|
|
the JSON protocol. So on startup we split the streams: a private duplicate of
|
|
the original stdout carries the protocol, and fd 1 is redirected to fd 2 so all
|
|
library chatter lands on stderr instead.
|
|
|
|
Protocol (one JSON object per line, on the protocol channel):
|
|
<- {"text": "...", "out": "/abs/path.wav", "speed": 1.3}
|
|
-> {"ok": true, "out": "/abs/path.wav", "ms": 123}
|
|
-> {"ok": false, "error": "..."}
|
|
On startup, once the model is ready, it emits exactly one line:
|
|
-> {"ready": true, "ms": <load-ms>, "device": "cpu"}
|
|
"""
|
|
|
|
import json
|
|
import os
|
|
import sys
|
|
import time
|
|
|
|
# Split protocol from library noise BEFORE importing anything heavy.
|
|
_proto = os.fdopen(os.dup(1), "w", buffering=1) # private copy of real stdout
|
|
os.dup2(2, 1) # fd1 -> stderr, so stray library prints don't hit the protocol
|
|
|
|
|
|
def _emit(obj: dict) -> None:
|
|
_proto.write(json.dumps(obj) + "\n")
|
|
_proto.flush()
|
|
|
|
|
|
def _log(*a):
|
|
print(*a, file=sys.stderr, flush=True)
|
|
|
|
|
|
def main() -> None:
|
|
lang = "KR"
|
|
device = os.environ.get("WSAI_MELO_DEVICE", "cpu") # "cpu" | "cuda" | "auto"
|
|
t0 = time.monotonic()
|
|
from melo.api import TTS # heavy import; only in the melo venv
|
|
|
|
tts = TTS(language=lang, device=device)
|
|
speaker_id = tts.hps.data.spk2id[lang]
|
|
load_ms = int((time.monotonic() - t0) * 1000)
|
|
_emit({"ready": True, "ms": load_ms, "device": device})
|
|
_log(f"[melo_worker] model ready in {load_ms} ms on {device}")
|
|
|
|
for line in sys.stdin:
|
|
line = line.strip()
|
|
if not line:
|
|
continue
|
|
try:
|
|
req = json.loads(line)
|
|
text = req["text"]
|
|
out = req["out"]
|
|
speed = float(req.get("speed", 1.0))
|
|
if out.startswith("/tmp") or out.startswith("/dev/shm"):
|
|
raise ValueError(f"refusing RAM-backed tmpfs path: {out}")
|
|
s = time.monotonic()
|
|
tts.tts_to_file(text, speaker_id, out, speed=speed)
|
|
ms = int((time.monotonic() - s) * 1000)
|
|
_emit({"ok": True, "out": out, "ms": ms})
|
|
except Exception as exc: # keep the worker alive across bad requests
|
|
_emit({"ok": False, "error": f"{type(exc).__name__}: {exc}"})
|
|
_log(f"[melo_worker] error: {exc}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|