mirror of
https://github.com/CCExtractor/ccextractor.git
synced 2026-02-04 05:44:53 +00:00
6f2a73d706
- Add docs/VOBSUB.md explaining the VOBSUB extraction workflow - Add tools/vobsubocr/Dockerfile for building subtile-ocr OCR tool - Document how to convert VOBSUB (.idx/.sub) to SRT using OCR The Dockerfile uses subtile-ocr (https://github.com/gwen-lg/subtile-ocr), an actively maintained fork of vobsubocr with better accuracy. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
36 lines
877 B
Docker
36 lines
877 B
Docker
# Dockerfile for subtile-ocr - VOBSUB to SRT converter
|
|
# Uses subtile-ocr, an actively maintained fork of vobsubocr
|
|
# https://github.com/gwen-lg/subtile-ocr
|
|
|
|
FROM ubuntu:22.04
|
|
|
|
# Prevent interactive prompts during package installation
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
|
|
# Install build dependencies
|
|
RUN apt-get update && apt-get install -y \
|
|
build-essential \
|
|
clang \
|
|
pkg-config \
|
|
libleptonica-dev \
|
|
libtesseract-dev \
|
|
tesseract-ocr \
|
|
tesseract-ocr-eng \
|
|
curl \
|
|
git \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Install Rust
|
|
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
|
|
ENV PATH="/root/.cargo/bin:${PATH}"
|
|
|
|
# Install subtile-ocr from git
|
|
RUN cargo install --git https://github.com/gwen-lg/subtile-ocr
|
|
|
|
# Create working directory
|
|
WORKDIR /data
|
|
|
|
# Default command shows help
|
|
ENTRYPOINT ["subtile-ocr"]
|
|
CMD ["--help"]
|