Initial commit: InkFlow — EPUB vers livre audio local (MLX/Kokoro)

2026-06-21 00:10:11 +02:00
commit d3bb91394b
71 changed files with 8138 additions and 0 deletions
--- a/backend/scripts/setup_models.py
+++ b/backend/scripts/setup_models.py
@@ -0,0 +1,87 @@
+#!/usr/bin/env python
+"""Verifie l'environnement InkFlow et pre-telecharge les modeles MLX.
+
+Usage :
+    python scripts/setup_models.py            # tout verifier + telecharger
+    python scripts/setup_models.py --check    # verifier sans telecharger
+
+Pre-requis systeme : Apple Silicon, Python >= 3.11, ffmpeg (brew install ffmpeg).
+"""
+from __future__ import annotations
+
+import argparse
+import platform
+import shutil
+import sys
+
+# Permet de lancer le script directement depuis backend/.
+sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parents[1]))
+
+from inkflow.config import (  # noqa: E402
+    GEMMA_MODEL,
+    KOKORO_MODEL,
+    QWEN3_TTS_MODEL,
+    ensure_dirs,
+)
+
+
+def check_env() -> bool:
+    ok = True
+    print(f"• Plateforme       : {platform.platform()} ({platform.machine()})")
+    if platform.machine() != "arm64":
+        print("  ! Attendu arm64 (Apple Silicon) — MLX ne sera pas optimal.")
+    print(f"• Python           : {sys.version.split()[0]}")
+    if sys.version_info < (3, 11):
+        print("  ! Python >= 3.11 requis."); ok = False
+
+    for mod in ("mlx", "mlx_lm", "mlx_audio", "ebooklib", "bs4",
+                "soundfile", "mutagen", "fastapi"):
+        try:
+            __import__(mod)
+            print(f"• import {mod:12s}: OK")
+        except Exception as exc:  # noqa: BLE001
+            print(f"• import {mod:12s}: ECHEC ({exc})"); ok = False
+
+    ff = shutil.which("ffmpeg")
+    print(f"• ffmpeg           : {ff or 'INTROUVABLE — brew install ffmpeg'}")
+    ok = ok and bool(ff)
+    return ok
+
+
+def download_lm(model_id: str) -> None:
+    from mlx_lm import load
+    print(f"  -> LM   {model_id}")
+    load(model_id)
+
+
+def download_tts(model_id: str) -> None:
+    from mlx_audio.tts.utils import load_model
+    print(f"  -> TTS  {model_id}")
+    load_model(model_id)
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--check", action="store_true", help="verifier sans telecharger")
+    args = ap.parse_args()
+
+    ensure_dirs()
+    print("== Verification de l'environnement ==")
+    env_ok = check_env()
+
+    if args.check:
+        return 0 if env_ok else 1
+    if not env_ok:
+        print("\nEnvironnement incomplet — corrige les points ci-dessus avant de continuer.")
+        return 1
+
+    print("\n== Telechargement des modeles (peut etre long la 1re fois) ==")
+    download_lm(GEMMA_MODEL)
+    download_tts(KOKORO_MODEL)
+    download_tts(QWEN3_TTS_MODEL)
+    print("\nTout est pret.")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())