"""Stage: MeloTTS Korean speed on the GPU (runs in its own Python 3.11 venv).""" from __future__ import annotations import os import sys import time from pathlib import Path sys.path.insert(0, str(Path(__file__).resolve().parent.parent)) from m0lib.common import StageResult, gpu_memory_mib, say, stage_args, stats # noqa: E402 SENTENCES = { "short": ["네, 알겠습니다.", "지금 바로 틀어 드릴게요.", "서울은 지금 맑습니다."], "medium": ["오늘 서울은 맑고 낮 최고 기온은 십삼 도까지 오르겠습니다.", "내일 아침 일곱 시에 알람을 맞춰 두었습니다. 푹 주무세요.", "두 번째 모니터에는 메모장과 크롬 창이 함께 떠 있습니다."], "long": ["회의는 오후 세 시에 시작해서 다섯 시쯤 끝날 예정이고, 끝난 뒤에는 저녁 메뉴를 같이 정하기로 하셨습니다. " "필요하시면 회의 삼십 분 전에 한 번 더 알려 드릴게요."], } def prepare_nltk(folder: Path) -> list[str]: """Fetch the English g2p data MeloTTS imports into the work folder (not the user profile).""" import nltk folder.mkdir(parents=True, exist_ok=True) os.environ["NLTK_DATA"] = str(folder) nltk.data.path.insert(0, str(folder)) got = [] for pkg, path in (("cmudict", "corpora/cmudict"), ("averaged_perceptron_tagger_eng", "taggers/averaged_perceptron_tagger_eng"), ("averaged_perceptron_tagger", "taggers/averaged_perceptron_tagger")): if not (folder / (path + ".zip")).exists() and not (folder / path).exists(): nltk.download(pkg, download_dir=str(folder), quiet=True) got.append(pkg) if os.name == "posix": # newer nltk refuses data folders that others can write to for root, dirs, files in os.walk(folder): for n in dirs + files: p = os.path.join(root, n) os.chmod(p, os.stat(p).st_mode & ~0o022) os.chmod(folder, os.stat(folder).st_mode & ~0o022) return got def korean_only_patches() -> list[str]: """Make MeloTTS Korean work without the Japanese MeCab, on Windows too. melo imports its Japanese front end (module-level ``MeCab.Tagger()``) even for Korean, and on Windows g2pkk asks for the ``eunjeon`` package instead of python-mecab-ko. Both are replaced here; v2 will need the same. """ import importlib import types done = [] try: import MeCab # noqa: F401 MeCab.Tagger # noqa: B018 except Exception: stub = types.ModuleType("MeCab") class Tagger: # Japanese text is never synthesised in M0 def __init__(self, *a, **k): pass def parse(self, text): raise RuntimeError("Japanese MeCab is not installed") stub.Tagger = Tagger sys.modules["MeCab"] = stub done.append("MeCab stub") import g2pkk.g2pkk as g2p_mod if g2p_mod.platform.system() == "Windows": g2p_mod.G2p.check_mecab = lambda self: None g2p_mod.G2p.get_mecab = lambda self: importlib.import_module("mecab").MeCab() done.append("g2pkk uses python-mecab-ko") return done def main() -> int: out, work, opts = stage_args() r = StageResult("tts_melo", out) os.environ.setdefault("HF_HOME", str(work / "models" / "hf")) audio_dir = out.parent / "audio" audio_dir.mkdir(parents=True, exist_ok=True) try: r["nltk"] = prepare_nltk(work / "models" / "nltk_data") r["patches"] = korean_only_patches() import numpy as np import soundfile as sf import torch from melo.api import TTS r["versions"] = {"torch": torch.__version__, "cuda": torch.version.cuda, "cuda_available": torch.cuda.is_available(), "gpu": torch.cuda.get_device_name(0) if torch.cuda.is_available() else None} except Exception as e: r.error("import", e) r.save("failed") return 0 device = "cuda" if torch.cuda.is_available() else "cpu" try: before = gpu_memory_mib() t0 = time.perf_counter() model = TTS(language="KR", device=device) spk = model.hps.data.spk2id["KR"] r["load_s"] = round(time.perf_counter() - t0, 2) t0 = time.perf_counter() model.tts_to_file("워밍업입니다.", spk, None, speed=1.0, quiet=True) r["first_synth_s"] = round(time.perf_counter() - t0, 2) after = gpu_memory_mib() if before and after: r["vram_model_mib"] = after[0] - before[0] sr = model.hps.data.sampling_rate say(f" 로딩 {r['load_s']}s, 첫 합성(워밍업) {r['first_synth_s']}s, VRAM 약 {r.get('vram_model_mib')} MiB") except Exception as e: r.error("load", e) r.save("failed") return 0 for speed in (1.0, 1.5): rows = [] for kind, texts in SENTENCES.items(): for text in texts: for i in range(2): if device == "cuda": torch.cuda.synchronize() t0 = time.perf_counter() wav = model.tts_to_file(text, spk, None, speed=speed, quiet=True) if device == "cuda": torch.cuda.synchronize() sec = time.perf_counter() - t0 dur = len(wav) / sr rows.append({"kind": kind, "chars": len(text), "seconds": round(sec, 3), "audio_s": round(dur, 2), "rtf": round(sec / dur, 3), "try": i + 1}) if kind != "short": name = f"melo_{kind}_{str(speed).replace('.', '_')}.wav" sf.write(str(audio_dir / name), np.asarray(wav, dtype=np.float32), sr) r[f"speed_{speed}"] = {"rows": rows, **{k: stats(x["seconds"] for x in rows if x["kind"] == k) for k in SENTENCES}, "rtf": stats(x["rtf"] for x in rows)} say(f" 속도 {speed}: 짧은 문장 {r[f'speed_{speed}']['short'].get('median')}s, " f"보통 문장 {r[f'speed_{speed}']['medium'].get('median')}s") r["device"] = device r["audio_files"] = sorted(p.name for p in audio_dir.glob("melo_*.wav")) r.save("ok" if not r["errors"] else "partial") return 0 if __name__ == "__main__": sys.exit(main())