| """Write pivo_runner's inputs for one or more texts: the author's frontend turns each text into phone ids. |
| |
| For text k (0, 1, ...) in the given order, <out>/<k as 3 digits>_tokens.i32 holds the phone ids (int32, little endian) |
| and <k>_voice.i32 one int32 (0 = Pi, 1 = Vo); index.tsv lists them. The runner reads them with --fixtures <out> |
| --count <number of texts>. |
| |
| Run from the repository root (the host's packages: pip install -r host/requirements.txt): |
| python runner/make_inputs.py --out inputs "NASA is ready for the next mission." |
| python runner/make_inputs.py --out inputs --voice Vo "Hello, my name is Vo." "Good morning." |
| """ |
| import argparse |
| import os |
| import sys |
|
|
| import numpy as np |
|
|
| ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) |
| sys.path.insert(0, os.path.join(ROOT, "host")) |
|
|
| from pivo.text import SPECIAL, VOICE_IDS, phonemize |
|
|
| MAX_TOKENS = 512 |
|
|
|
|
| def main(): |
| ap = argparse.ArgumentParser() |
| ap.add_argument("texts", nargs="+") |
| ap.add_argument("--out", required=True) |
| ap.add_argument("--voice", choices=sorted(VOICE_IDS), default="Pi") |
| a = ap.parse_args() |
| os.makedirs(a.out, exist_ok=True) |
| rows = ["# id3\tvoice\ttokens\ttext"] |
| for k, text in enumerate(a.texts): |
| front = phonemize(text) |
| if not any(s not in SPECIAL for s in front.symbols): |
| raise SystemExit(f"text {k}: no spoken text") |
| if len(front.token_ids) > MAX_TOKENS: |
| raise SystemExit(f"text {k}: {len(front.token_ids)} tokens > {MAX_TOKENS}; split it") |
| id3 = f"{k:03d}" |
| np.array(front.token_ids, "<i4").tofile(os.path.join(a.out, f"{id3}_tokens.i32")) |
| np.array([VOICE_IDS[a.voice]], "<i4").tofile(os.path.join(a.out, f"{id3}_voice.i32")) |
| rows.append(f"{id3}\t{a.voice}\t{len(front.token_ids)}\t{text}") |
| with open(os.path.join(a.out, "index.tsv"), "w", encoding="utf-8") as f: |
| f.write("\n".join(rows) + "\n") |
| print(f"{len(a.texts)} inputs in {a.out}: run pivo_runner with --fixtures {a.out} --count {len(a.texts)}") |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
