pierreandLetta Code
bcd48a3443
- playback.zig: sentence queue + playback thread — agent reply chunks are split on sentence boundaries and each sentence is synthesized+played as it completes, so voice starts after the first sentence, not after the reply - melo_server.py v2: WAV written to /dev/shm, raw s16le PCM + sample rate streamed over stdout (WAV n rate header + bytes), file deleted immediately; melo stdout chatter rerouted to stderr to keep the protocol clean - melo.zig: speakRaw returns in-memory PCM; pw-play fed via stdin pipe (no on-disk TTS files at all) - whisper: --language auto - fix: double-close of pw-play stdin panicked Threaded Io in debug - fix: quit-path frees for transcript cache, bubble lists, sentence queue, reply buffer (debug allocator leak panic) 👾 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta Code <noreply@letta.com>
112 lines
3.7 KiB
Python
112 lines
3.7 KiB
Python
#!/usr/bin/env python3
|
|
"""MeloTTS server for inferon.
|
|
|
|
Long-running subprocess: loads the MeloTTS model once, then reads lines of
|
|
text on stdin and writes "<wav-path> <duration-seconds>" per line on stdout.
|
|
stderr passes through for logging.
|
|
|
|
Protocol (v2, raw PCM):
|
|
-> one line of text to synthesize
|
|
<- header: "WAV <n_bytes> <sample_rate>\n" followed by <n_bytes> of raw s16le PCM
|
|
|
|
Synthesizes to /dev/shm (RAM-backed), streams bytes, deletes immediately.
|
|
Kill with SIGTERM.
|
|
"""
|
|
|
|
import sys
|
|
import os
|
|
import io
|
|
import time
|
|
import wave
|
|
import signal
|
|
import tempfile
|
|
import warnings
|
|
|
|
warnings.filterwarnings("ignore")
|
|
|
|
MELO_ROOT = os.path.expanduser("~/Projects/MeloTTS")
|
|
CKPT = os.path.join(MELO_ROOT, "ckpt/MeloTTS-English-v3/checkpoint.pth")
|
|
CONFIG = os.path.join(MELO_ROOT, "ckpt/MeloTTS-English-v3/config.json")
|
|
OUT_DIR = "/tmp/inferon"
|
|
SPEAKER = "EN-Newest" # v3 English: single speaker (British-accented female)
|
|
LANG = "EN"
|
|
SPEED = 1.3 # speech rate; 1.0 = natural, higher = faster
|
|
|
|
sys.path.insert(0, MELO_ROOT)
|
|
|
|
|
|
def synth_bytes(path):
|
|
"""Read a WAV, return (raw s16le PCM, sample_rate), delete the file."""
|
|
with wave.open(path, "rb") as w:
|
|
rate = w.getframerate()
|
|
pcm = w.readframes(w.getnframes())
|
|
os.unlink(path)
|
|
return pcm, rate
|
|
|
|
|
|
def main() -> None:
|
|
signal.signal(signal.SIGTERM, lambda *_: sys.exit(0))
|
|
signal.signal(signal.SIGINT, lambda *_: sys.exit(0))
|
|
|
|
os.makedirs(OUT_DIR, exist_ok=True)
|
|
|
|
# Protocol handle — melo's progress chatter goes to stdout, so we keep
|
|
# this reference and then point stdout at stderr.
|
|
proto_out = sys.stdout.buffer
|
|
|
|
# Heavy imports inside main so signal handlers are installed first.
|
|
from melo.api import TTS
|
|
|
|
model = TTS(language=LANG, config_path=CONFIG, ckpt_path=CKPT)
|
|
|
|
speaker_ids = model.hps.data.spk2id
|
|
if SPEAKER not in speaker_ids:
|
|
# English v3 fallback: use the first speaker and say so on stderr.
|
|
fallback = next(iter(speaker_ids))
|
|
print(f"melo_server: speaker {SPEAKER!r} not in {list(speaker_ids)}; using {fallback!r}",
|
|
file=sys.stderr, flush=True)
|
|
speaker = fallback
|
|
else:
|
|
speaker = speaker_ids[SPEAKER]
|
|
|
|
# melo's progress chatter goes to stdout — keep the protocol clean.
|
|
sys.stdout = sys.stderr
|
|
|
|
# Warm up with a full sentence (longer text paths hit NLTK/num2words,
|
|
# which is where missing-data errors surface). Fail before READY.
|
|
fd, wpath = tempfile.mkstemp(suffix=".wav", dir="/dev/shm")
|
|
os.close(fd)
|
|
try:
|
|
model.tts_to_file("Warmup sentence number twelve, spoken on the first of January.",
|
|
speaker, wpath, speed=SPEED)
|
|
_ = synth_bytes(wpath) # exercise the full byte path before READY
|
|
finally:
|
|
if os.path.exists(wpath):
|
|
os.unlink(wpath)
|
|
|
|
# Ready marker — inferon waits for this before declaring the backend up.
|
|
proto_out.write(b"READY\n")
|
|
proto_out.flush()
|
|
|
|
for line in sys.stdin:
|
|
text = line.strip()
|
|
if not text:
|
|
continue
|
|
text = text[:2000] # protocol cap — extremely long replies get clipped
|
|
|
|
try:
|
|
fd, wpath = tempfile.mkstemp(suffix=".wav", dir="/dev/shm")
|
|
os.close(fd)
|
|
model.tts_to_file(text, speaker, wpath, speed=SPEED)
|
|
pcm, rate = synth_bytes(wpath)
|
|
proto_out.write(f"WAV {len(pcm)} {rate}\n".encode())
|
|
proto_out.write(pcm)
|
|
proto_out.flush()
|
|
except Exception as e: # noqa: BLE001 - protocol: report and survive
|
|
print(f"melo_server: synthesis failed: {e}", file=sys.stderr, flush=True)
|
|
print("ERROR", flush=True)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|