Repository files navigation

Pipeline is a simple and easy tools to create vertical (.vrt) and corpus files from videos.

It rests on this tools to create the pipeline:

• OpenAI Whisper: is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.
• Spacy: is a free, open-source library for Natural Language Processing in Python. It features NER, POS tagging, dependency parsing, word vectors and more.
• Gentle: is a forced aligner for speech and text. It uses a probabilistic model to align speech to text, and is trained on a large dataset of speech and text. It is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

Take a videofile as input and generate the corresponding vtt file namedvideofile.vtt in the same directory.

Install next dependencies to make it work:

Requires the command-line toolffmpeg to be installed on your system, which is available from most package managers:

# on Ubuntu or Debiansudo apt update&& sudo apt install ffmpeg# on MacOS using Homebrew (https://brew.sh/)brew install ffmpeg# on Windows using Chocolatey (https://chocolatey.org/)choco install ffmpeg

Requires spacy models:

Requires to install gentle fromhere and be in your path.