51811ad251
Both voice backends defaulted to CPU. Fix the "CUDA unavailable" gaps so everything that benefits from the RTX 5050 uses it: - MeloTTS venv had CPU-only torch (2.12.0+cpu) -> installed Blackwell-capable torch/torchaudio 2.11.0+cu128 (sm_120 verified with a real GPU matmul). - faster-whisper CUDA loaded but transcribe() died with "libcublas.so.12 not found": installed nvidia-cublas-cu12 + nvidia-cudnn-cu12 into the whisper venv and inject those nvidia/*/lib dirs into the worker's LD_LIBRARY_PATH at spawn (the loader only honours it at exec). - WSAI_WHISPER_DEVICE / WSAI_MELO_DEVICE now default to "auto": pick CUDA when present, else CPU, and each worker falls back to CPU if a CUDA load fails so the voice loop never dies on a GPU-less host. Verified end-to-end through the real backend classes: both workers report "ready on cuda"; steady-state STT ~170ms (was ~1350ms CPU), TTS ~4s first call vs ~23s CPU. All 12 tests pass. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
107 lines
3.9 KiB
Python
107 lines
3.9 KiB
Python
"""Persistent faster-whisper STT worker.
|
|
|
|
faster-whisper (ctranslate2) lives in its own Python (whisper312); loading the
|
|
model takes seconds, so we load it ONCE here and then serve transcription
|
|
requests over stdin/stdout. This process is launched with the whisper312
|
|
interpreter by wsai.backends.whisper.WhisperSTT.
|
|
|
|
Like the MeloTTS worker, model/backend chatter could 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 any library print lands
|
|
on stderr instead (where the parent drains it for diagnostics).
|
|
|
|
Protocol (one JSON object per line, on the protocol channel):
|
|
<- {"wav": "/abs/path.wav", "language": "ko"}
|
|
-> {"ok": true, "text": "...", "language": "ko", "ms": 123}
|
|
-> {"ok": false, "error": "..."}
|
|
On startup, once the model is ready, it emits exactly one line:
|
|
-> {"ready": true, "ms": <load-ms>, "device": "cpu", "model": "small"}
|
|
"""
|
|
|
|
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, ensure_ascii=False) + "\n")
|
|
_proto.flush()
|
|
|
|
|
|
def _log(*a):
|
|
print(*a, file=sys.stderr, flush=True)
|
|
|
|
|
|
def main() -> None:
|
|
model_name = os.environ.get("WSAI_WHISPER_MODEL", "small")
|
|
requested = os.environ.get("WSAI_WHISPER_DEVICE", "auto") # cpu | cuda | auto
|
|
default_lang = os.environ.get("WSAI_WHISPER_LANGUAGE", "ko") or None
|
|
|
|
from faster_whisper import WhisperModel # heavy import; only in whisper venv
|
|
|
|
def _has_cuda() -> bool:
|
|
try:
|
|
import ctranslate2
|
|
|
|
return ctranslate2.get_cuda_device_count() > 0
|
|
except Exception:
|
|
return False
|
|
|
|
device = requested
|
|
if requested == "auto":
|
|
device = "cuda" if _has_cuda() else "cpu"
|
|
|
|
def _compute_for(dev: str) -> str:
|
|
# int8 on CPU keeps a small model fast; float16 is the usual CUDA choice.
|
|
return os.environ.get(
|
|
"WSAI_WHISPER_COMPUTE", "int8" if dev == "cpu" else "float16"
|
|
)
|
|
|
|
t0 = time.monotonic()
|
|
try:
|
|
model = WhisperModel(model_name, device=device, compute_type=_compute_for(device))
|
|
except Exception as exc:
|
|
# CUDA picked but unusable (missing libs, OOM): fall back to CPU rather
|
|
# than leaving the whole voice loop dead.
|
|
if device == "cuda":
|
|
_log(f"[whisper_worker] CUDA load failed ({exc}); falling back to CPU")
|
|
device = "cpu"
|
|
model = WhisperModel(model_name, device=device, compute_type=_compute_for(device))
|
|
else:
|
|
raise
|
|
compute = _compute_for(device)
|
|
load_ms = int((time.monotonic() - t0) * 1000)
|
|
_emit({"ready": True, "ms": load_ms, "device": device, "model": model_name})
|
|
_log(f"[whisper_worker] {model_name} ready in {load_ms} ms on {device}/{compute}")
|
|
|
|
for line in sys.stdin:
|
|
line = line.strip()
|
|
if not line:
|
|
continue
|
|
try:
|
|
req = json.loads(line)
|
|
wav = req["wav"]
|
|
language = req.get("language", default_lang)
|
|
s = time.monotonic()
|
|
segments, info = model.transcribe(
|
|
wav,
|
|
language=language,
|
|
beam_size=int(req.get("beam_size", 5)),
|
|
vad_filter=bool(req.get("vad_filter", True)),
|
|
)
|
|
text = "".join(seg.text for seg in segments).strip()
|
|
ms = int((time.monotonic() - s) * 1000)
|
|
_emit({"ok": True, "text": text, "language": info.language, "ms": ms})
|
|
except Exception as exc: # keep the worker alive across bad requests
|
|
_emit({"ok": False, "error": f"{type(exc).__name__}: {exc}"})
|
|
_log(f"[whisper_worker] error: {exc}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|