diff options
Diffstat (limited to 'tools/make_faster_voices_json.py')
| -rwxr-xr-x | tools/make_faster_voices_json.py | 121 |
1 files changed, 0 insertions, 121 deletions
diff --git a/tools/make_faster_voices_json.py b/tools/make_faster_voices_json.py deleted file mode 100755 index 2e00f72..0000000 --- a/tools/make_faster_voices_json.py +++ /dev/null @@ -1,121 +0,0 @@ -#!/usr/bin/env python3 -"""Generate a voices.json file for the faster-qwen3-tts server. - -Scans a directory for .wav files, transcribes each with a local Whisper -backend (faster_whisper or whisper), and writes a voices.json - -Usage: - python tools/make_faster_voices_json.py INPUT_DIR [--output PATH] - [--language LANG] - [--whisper-model NAME] [--force] - -The output can be passed to the faster server: - python examples/openai_server.py --voices voices.json --port 8000 -""" - -import argparse -import json -import sys -from pathlib import Path - -# Allow running from any working directory. -sys.path.insert(0, str(Path(__file__).resolve().parent.parent)) - -from converter.tts import normalize_language, transcribe_reference_audio - - -def find_wav_files(input_dir: Path) -> list: - """Return the .wav files in INPUT_DIR, sorted alphabetically by name.""" - return sorted( - (path for path in input_dir.iterdir() - if path.is_file() and path.suffix.lower() == ".wav"), - key=lambda path: path.name.lower(), - ) - - -def prompt_overwrite(output_path: Path) -> bool: - """Ask whether to overwrite an existing output file.""" - while True: - try: - answer = input(f"{output_path} already exists. Overwrite? (y/n): ").strip().lower() - except EOFError: - print("\n[WARNING] No interactive input available; keeping existing file") - return False - if answer in ("y", "yes"): - return True - if answer in ("n", "no"): - return False - print("Please answer 'y' or 'n'.") - - -def build_voices(wav_files: list, language: str, whisper_model: str) -> dict: - """Transcribe each wav file and build the voices mapping.""" - voices = {} - for wav_file in wav_files: - name = wav_file.stem - print(f"[INFO] Transcribing {wav_file.name} (voice '{name}')...") - text = transcribe_reference_audio(str(wav_file), model_name=whisper_model) - if text: - print(f"[OK] {name}: {text}") - else: - print(f"[WARNING] No transcript for '{name}'; the faster backend " - "strongly recommends an accurate transcript — consider editing " - "voices.json by hand before starting the server") - voices[name] = { - "ref_audio": str(wav_file.resolve()), - "ref_text": text or "", - "language": language, - } - return voices - - -def main() -> int: - parser = argparse.ArgumentParser( - description="Generate a voices.json for the faster-qwen3-tts server " - "from a directory of .wav reference files.") - parser.add_argument("input_dir", type=Path, - help="Directory containing .wav reference audio files") - parser.add_argument("--output", type=Path, default=None, - help="Output path for voices.json " - "(default: INPUT_DIR/voices.json)") - parser.add_argument("--language", type=str, default="English", - help="Language for all voices, as passed to the TTS model " - "(default: English; names and short codes accepted)") - parser.add_argument("--whisper-model", type=str, default="base", - help="Whisper model size for transcription " - "(default: base)") - parser.add_argument("--force", action="store_true", - help="Overwrite the output file without prompting") - args = parser.parse_args() - - try: - language = normalize_language(args.language) - except ValueError as exc: - parser.error(str(exc)) - - if not args.input_dir.is_dir(): - parser.error(f"Input directory not found: {args.input_dir}") - - wav_files = find_wav_files(args.input_dir) - if not wav_files: - parser.error(f"No .wav files found in {args.input_dir}") - - output_path = args.output if args.output is not None \ - else args.input_dir / "voices.json" - if output_path.exists() and not args.force and not prompt_overwrite(output_path): - print("[INFO] Aborted; existing voices.json kept") - return 1 - - voices = build_voices(wav_files, language, args.whisper_model) - - with output_path.open("w", encoding="utf-8") as handle: - json.dump(voices, handle, indent=4, ensure_ascii=False) - handle.write("\n") - - print(f"[OK] Wrote {output_path} with {len(voices)} voice(s): " - f"{', '.join(voices)}") - return 0 - - -if __name__ == "__main__": - sys.exit(main()) |
