subaligner 0.0.11

Automatically synchronise subtitles to companion audiovisual content with Deep Neural Network and Forced Alignment.

Dependencies

FFmpeg and eSpeak

$ apt-get install ffmpeg espeak libespeak1 libespeak-dev espeak-data

or

$ brew install ffmpeg espeak

Installation

# Install from PyPI (pre-emptive NumPy)
$ pip install numpy 
$ pip install subaligner

or

# Install via pipx
pipx install subaligner

or

# Install from GitHub via Pipenv
...
[packages]
numpy = "*"
subaligner = {git = "ssh://[e-mail]/baxtree/subaligner.git", ref = "<TAG>"}
...

or

# Install from source

$ git clone [e-mail]:baxtree/subaligner.git
$ cd subaligner
$ make install && source .venv/bin/activate

or

# Use dockerised installation

$ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner bash

Usage

# Single-stage alignment (high-level shift with lower latency)

$ subaligner_1pass -v video.mp4 -s subtitle.srt

# Dual-stage alignment (low-level shift with higher latency)

$ subaligner_2pass -v video.mp4 -s subtitle.srt

or

# Pass in single-stage or dual-stage as the alignment mode

$ subaligner -m single -v video.mp4 -s subtitle.srt
$ subaligner -m dual -v video.mp4 -s subtitle.srt

# Run alignments with pipx

$ pipx run subaligner -m single -v video.mp4 -s subtitle.srt
$ pipx run subaligner -m dual -v video.mp4 -s subtitle.srt

# Run the module as a script
$ python -m subaligner -m single -v video.mp4 -s subtitle.srt
$ python -m subaligner -m dual -v video.mp4 -s subtitle.srt
$ python -m subaligner.subaligner_1pass -v video.mp4 -s subtitle.srt
$ python -m subaligner.subaligner_2pass -v video.mp4 -s subtitle.srt

# Run alignments with the docker image

$ docker pull baxtree/subaligner
$ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner_1pass -v video.mp4 -s subtitle.srt
$ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner_2pass -v video.mp4 -s subtitle.srt

The aligned subtitle will be saved at subtitle_aligned.srt. For details on CLI, run subaligner_1pass --help, subaligner_2pass --help or subaligner --help.

Supported Formats

Subtitle: SubRip, TTML, WebVTT, (Advanced) SubStation Alpha, MicroDVD, MPL2 and TMP

Video: MP4, WebM, Ogg, 3GP, FLV and MOV

Anatomy

Subtitles can be out of sync with their companion audiovisual media files for a variety of causes including latency introduced by Speech-To-Text on live streams or calibration and rectification involving human intervention during post-production.

A model has been trained with synchronised video and subtitle pairs and later used for predicating shifting offsets and directions under the guidance of a two-stage aligning approach.

First Stage (Global Alignment):

Second Stage (Parallelised Individual Alignment):