Improve subtitle merge, gender-aware xưng hô, Colab tuning, add tests

Colab: CTX_SIZE 8192 to reduce context overflow errors

Merge scene vision + translation into single call; 1 frame per cue at start

Colab: default FORCE_LLAMA_REBUILD=False to use Drive cache

Fix llama.cpp pin: clone tag b9553 instead of short commit ref

Colab: MTP config (FORCE_LLAMA_REBUILD, CTX_SIZE, scene speed options)

Update pipeline + slim Colab notebook (HF-only code source)

Auto-rebuild llama-server >= b9549 for Gemma 4 MTP

Update colab/GemmaSRT_Colab.ipynb (HF_TOKEN empty)

Update colab/GemmaSRT_Colab.ipynb

age/gender: robust post_init + dict tied keys; add model preflight in notebook

Colab: numpy/lightning fix, pyannote Agree URLs, diarize errors

Colab: pin numpy<2.1 for pyannote

Colab: verify models + pyannote before pipeline

Fix colab/GemmaSRT_Colab.ipynb JSON (HF_TOKEN sanitize)

Docs: how to open Colab when repo is private (401 fix)

Colab: ENABLE_DIARIZE=True by default

Colab: HF_TOKEN auth for private repo (Secrets or config cell)

Add Pass 0 speaker diarization (age/gender) to Colab + secret-free token loading

Clarify notebook docs: SKIP_CORRECTION default True, pipeline table

Default SKIP_CORRECTION=True (skip OCR by default)

Loosen subtitle budget; disable Pass 2b shorten by default

Merge adjacent cue pairs for wider dubbing timestamps

Remove build cell; restore llama-server from Drive tgz only

Colab: fix llama-server shared build, cache llama-server-bin.tgz

Fix llama-server Drive cache: tar.gz + size checks

Colab: PHIM_STEMS, live build log, resume build, Gemma/Phim

Fix llama-server build on Colab T4: nvcc, CUDA env, verbose errors

Colab: PHIM_STEMS, Gemma/Phim, robust llama-server build

Drive layout: Gemma/Cache + Gemma/Phim folders

Add auto disconnect Drive and Colab runtime after jobs complete

Colab: JOBS queue for sequential multi-movie translation

Initial upload: Gemma SRT Translate + Colab notebook