92 lines
4.0 KiB
Python
92 lines
4.0 KiB
Python
"""Banque de voix : un jeu de voix variees (genre/age) auto-suffisant.
|
|
|
|
Chaque voix s'appuie sur une voix Kokoro (identite + clip de reference). Le clip
|
|
de reference est genere une fois en lisant un passage francais standard ; il sert
|
|
de reference de timbre pour le clonage Qwen3 (rendu final). Aucune ressource
|
|
externe a sourcer.
|
|
|
|
Resolution moteur :
|
|
- Kokoro -> VoiceSpec(preset=kokoro_voice) (rapide, preview / draft)
|
|
- Qwen3 -> VoiceSpec(ref_audio=clip, ref_text=…) (qualite, clonage)
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import soundfile as sf
|
|
|
|
from ..config import VOICEBANK_DIR
|
|
from ..models import VoiceEntry, Voicebank
|
|
from ..tts.base import VoiceSpec
|
|
|
|
# Passage de reference lu par chaque voix pour creer son clip de clonage.
|
|
REFERENCE_TEXT = (
|
|
"L'univers est toujours plus étrange qu'on ne le croit. "
|
|
"Chaque nouvelle merveille pose les bases d'une découverte plus éblouissante encore."
|
|
)
|
|
|
|
# Jeu de voix par defaut (varie en genre). ff_siwis est la seule voix FR native ;
|
|
# les autres empruntent un timbre anglais mais lisent un texte phonemise en FR.
|
|
SEED: list[VoiceEntry] = [
|
|
VoiceEntry(id="fr_f_siwis", kokoro_voice="ff_siwis", gender="female", age="adult", label="Siwis (FR)"),
|
|
VoiceEntry(id="f_bella", kokoro_voice="af_bella", gender="female", age="adult", label="Bella"),
|
|
VoiceEntry(id="f_heart", kokoro_voice="af_heart", gender="female", age="young", label="Heart"),
|
|
VoiceEntry(id="f_emma", kokoro_voice="bf_emma", gender="female", age="adult", label="Emma"),
|
|
VoiceEntry(id="f_nicole", kokoro_voice="af_nicole", gender="female", age="adult", label="Nicole"),
|
|
VoiceEntry(id="m_fenrir", kokoro_voice="am_fenrir", gender="male", age="adult", label="Fenrir"),
|
|
VoiceEntry(id="m_michael", kokoro_voice="am_michael", gender="male", age="adult", label="Michael"),
|
|
VoiceEntry(id="m_george", kokoro_voice="bm_george", gender="male", age="adult", label="George"),
|
|
VoiceEntry(id="m_lewis", kokoro_voice="bm_lewis", gender="male", age="adult", label="Lewis"),
|
|
VoiceEntry(id="m_eric", kokoro_voice="am_eric", gender="male", age="young", label="Eric"),
|
|
VoiceEntry(id="m_santa", kokoro_voice="am_santa", gender="male", age="old", label="Santa"),
|
|
]
|
|
|
|
|
|
def metadata_path() -> Path:
|
|
return VOICEBANK_DIR / "metadata.json"
|
|
|
|
|
|
def clips_dir() -> Path:
|
|
return VOICEBANK_DIR / "clips"
|
|
|
|
|
|
def load_voicebank() -> Voicebank:
|
|
path = metadata_path()
|
|
if path.exists():
|
|
return Voicebank.model_validate_json(path.read_text(encoding="utf-8"))
|
|
return Voicebank(entries=list(SEED))
|
|
|
|
|
|
def save_voicebank(vb: Voicebank) -> Path:
|
|
VOICEBANK_DIR.mkdir(parents=True, exist_ok=True)
|
|
metadata_path().write_text(vb.model_dump_json(indent=2), encoding="utf-8")
|
|
return metadata_path()
|
|
|
|
|
|
def build_voicebank(*, regenerate: bool = False) -> Voicebank:
|
|
"""Genere les clips de reference manquants et ecrit metadata.json."""
|
|
from ..tts.kokoro import KokoroBackend
|
|
|
|
clips_dir().mkdir(parents=True, exist_ok=True)
|
|
backend = KokoroBackend()
|
|
entries: list[VoiceEntry] = []
|
|
for seed in SEED:
|
|
clip_rel = f"clips/{seed.id}.wav"
|
|
clip_abs = VOICEBANK_DIR / clip_rel
|
|
if regenerate or not clip_abs.exists():
|
|
audio, sr = backend.synthesize(REFERENCE_TEXT, VoiceSpec(preset=seed.kokoro_voice))
|
|
sf.write(str(clip_abs), audio, sr)
|
|
entry = seed.model_copy(update={"ref_audio": clip_rel, "ref_text": REFERENCE_TEXT})
|
|
entries.append(entry)
|
|
vb = Voicebank(entries=entries)
|
|
save_voicebank(vb)
|
|
return vb
|
|
|
|
|
|
def voice_spec_for(entry: VoiceEntry, engine: str, *, speed: float = 1.0) -> VoiceSpec:
|
|
"""Construit la VoiceSpec adaptee au moteur cible."""
|
|
if engine == "qwen3" and entry.ref_audio:
|
|
ref_abs = str(VOICEBANK_DIR / entry.ref_audio)
|
|
return VoiceSpec(ref_audio=ref_abs, ref_text=entry.ref_text, speed=speed)
|
|
return VoiceSpec(preset=entry.kokoro_voice, speed=speed)
|