zenn
7101fdcd65
FastAPI backend, web UI, CosyVoice3/F5-TTS setup scripts, and handoff docs for GPU PC continuation. Co-authored-by: Cursor <cursoragent@cursor.com>
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
#!/usr/bin/env python3
|
|
"""F5-TTS 추론 워커 (f5tts venv에서 실행)."""
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
|
|
def main() -> int:
|
|
parser = argparse.ArgumentParser(description="F5-TTS inference worker")
|
|
parser.add_argument("--ref-audio", required=True, help="Reference WAV path")
|
|
parser.add_argument("--ref-text", required=True, help="Transcript of reference audio")
|
|
parser.add_argument("--gen-text", required=True, help="Text to synthesize")
|
|
parser.add_argument("--out", required=True, help="Output WAV path")
|
|
parser.add_argument("--model", default="F5TTS_v1_Base")
|
|
args = parser.parse_args()
|
|
|
|
ref = Path(args.ref_audio)
|
|
if not ref.is_file():
|
|
print(f"ref audio not found: {ref}", file=sys.stderr)
|
|
return 1
|
|
|
|
out = Path(args.out)
|
|
out.parent.mkdir(parents=True, exist_ok=True)
|
|
|
|
try:
|
|
from f5_tts.api import F5TTS
|
|
except ImportError as e:
|
|
print("f5-tts not installed. Run: ./scripts/setup_f5tts.sh", file=sys.stderr)
|
|
print(e, file=sys.stderr)
|
|
return 1
|
|
|
|
tts = F5TTS(model=args.model)
|
|
tts.infer(
|
|
ref_file=str(ref),
|
|
ref_text=args.ref_text,
|
|
gen_text=args.gen_text,
|
|
file_wave=str(out),
|
|
remove_silence=True,
|
|
)
|
|
print(f"OK: {out}")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|