110b2298b7
- stt_local: Whisper large-v3-turbo MLX, transcript + timestamped json - lipsync_local: Rhubarb visemes (CPU lane), dialog-guided - voice_clone_local: Chatterbox on MPS (needs setuptools<81 for perth/pkg_resources) - wan_video: Wan 2.2 TI2V-5B t2v/i2v via resident ComfyUI, frames->mp4 - llm_local: Qwen3-30B-A3B-4bit dialogue writer (primary-only) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
50 lines
1.5 KiB
Python
50 lines
1.5 KiB
Python
import argparse
|
|
import json
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
from pathlib import Path
|
|
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("--input", action="append", default=[])
|
|
ap.add_argument("--outdir", required=True)
|
|
ap.add_argument("--params", default="{}")
|
|
a = ap.parse_args()
|
|
p = json.loads(a.params)
|
|
|
|
if not a.input:
|
|
print("ERROR: needs one WAV/OGG input")
|
|
sys.exit(1)
|
|
|
|
root = Path(__file__).resolve().parents[3]
|
|
rhubarb = root / "vendor" / "rhubarb" / "rhubarb"
|
|
if not rhubarb.exists():
|
|
print("ERROR: rhubarb not installed — run scripts/install_rhubarb.sh")
|
|
sys.exit(1)
|
|
|
|
outdir = Path(a.outdir)
|
|
out_json = outdir / (Path(a.input[0]).stem + ".visemes.json")
|
|
cmd = [str(rhubarb), "-f", "json", "-o", str(out_json), a.input[0]]
|
|
if p.get("shapes", "extended") == "basic":
|
|
cmd += ["--extendedShapes", ""]
|
|
|
|
dialog = (p.get("dialog") or "").strip()
|
|
if dialog:
|
|
tmp = outdir / "work" # subdir: only top-level outdir files register as assets
|
|
tmp.mkdir(exist_ok=True)
|
|
dialog_file = tmp / "dialog.txt"
|
|
dialog_file.write_text(dialog + "\n")
|
|
cmd += ["--dialogFile", str(dialog_file)]
|
|
|
|
t0 = time.time()
|
|
r = subprocess.run(cmd, capture_output=True, text=True)
|
|
if r.stderr:
|
|
print(r.stderr[-1500:], file=sys.stderr)
|
|
if r.returncode != 0 or not out_json.exists():
|
|
print("ERROR: rhubarb failed")
|
|
sys.exit(1)
|
|
|
|
cues = json.loads(out_json.read_text())["mouthCues"]
|
|
print(f"done in {time.time() - t0:.1f}s: {len(cues)} mouth cues, "
|
|
f"{cues[-1]['end'] if cues else 0:.2f}s")
|