86 lines
2.2 KiB
Python
86 lines
2.2 KiB
Python
|
"""Silero TTS helper for J.A.R.V.I.S.
|
||
|
|
|
||
|
|
Reads text from stdin, synthesises with snakers4/silero-models, writes the result
|
||
|
|
to a temp wav, and prints the path on stdout. The Rust side then plays + deletes it.
|
||
|
|
|
||
|
|
Install:
|
||
|
|
pip install torch soundfile numpy
|
||
|
|
|
||
|
|
Usage (called by jarvis-core/src/tts/silero.rs):
|
||
|
|
echo "привет" | python silero_tts.py --voice xenia
|
||
|
|
|
||
|
|
Voices for ru_v3:
|
||
|
|
xenia (female, default), baya (female), aidar (male), eugene (male), kseniya (female).
|
||
|
|
"""
|
||
|
|
|
||
|
|
import argparse
|
||
|
|
import os
|
||
|
|
import sys
|
||
|
|
import tempfile
|
||
|
|
|
||
|
|
try:
|
||
|
|
import torch # type: ignore
|
||
|
|
except ImportError:
|
||
|
|
print("silero_tts: torch not installed. Run `pip install torch`.", file=sys.stderr)
|
||
|
|
sys.exit(2)
|
||
|
|
|
||
|
|
import warnings
|
||
|
|
|
||
|
|
warnings.filterwarnings("ignore")
|
||
|
|
|
||
|
|
_MODEL = None
|
||
|
|
|
||
|
|
|
||
|
|
def load_model(device: str = "cpu"):
|
||
|
|
global _MODEL
|
||
|
|
if _MODEL is None:
|
||
|
|
torch.set_num_threads(4)
|
||
|
|
_MODEL, _ = torch.hub.load(
|
||
|
|
repo_or_dir="snakers4/silero-models",
|
||
|
|
model="silero_tts",
|
||
|
|
language="ru",
|
||
|
|
speaker="v3_1_ru",
|
||
|
|
trust_repo=True,
|
||
|
|
)
|
||
|
|
_MODEL.to(torch.device(device))
|
||
|
|
return _MODEL
|
||
|
|
|
||
|
|
|
||
|
|
def synth(text: str, voice: str, sample_rate: int = 48000) -> str:
|
||
|
|
"""Synth text → return path to temp wav."""
|
||
|
|
model = load_model()
|
||
|
|
audio = model.apply_tts(text=text, speaker=voice, sample_rate=sample_rate)
|
||
|
|
|
||
|
|
import numpy as np
|
||
|
|
import soundfile as sf # type: ignore
|
||
|
|
|
||
|
|
fd, path = tempfile.mkstemp(prefix="jarvis-silero-", suffix=".wav")
|
||
|
|
os.close(fd)
|
||
|
|
sf.write(path, audio.numpy().astype(np.float32), sample_rate)
|
||
|
|
return path
|
||
|
|
|
||
|
|
|
||
|
|
def main() -> int:
|
||
|
|
ap = argparse.ArgumentParser()
|
||
|
|
ap.add_argument("--voice", default="xenia", help="speaker name (xenia, baya, aidar, eugene, kseniya)")
|
||
|
|
ap.add_argument("--sample-rate", type=int, default=48000)
|
||
|
|
args = ap.parse_args()
|
||
|
|
|
||
|
|
text = sys.stdin.read().strip()
|
||
|
|
if not text:
|
||
|
|
print("silero_tts: empty input", file=sys.stderr)
|
||
|
|
return 1
|
||
|
|
|
||
|
|
try:
|
||
|
|
path = synth(text, args.voice, args.sample_rate)
|
||
|
|
except Exception as exc:
|
||
|
|
print(f"silero_tts: synth failed: {exc}", file=sys.stderr)
|
||
|
|
return 3
|
||
|
|
|
||
|
|
print(path)
|
||
|
|
return 0
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
sys.exit(main())
|