openlrc 0.0.3

Transcribe and translate voice into LRC file.

Open-Lyrics

Open-Lyrics is a open-source project to transcribe ( using faster-whisper) voice file and translate/polish (OpenAI-GPT) the text.

This new project is rapidly underway, and we welcome any issues or pull requests.

Installation

1. Please install CUDA and cuDNN first according to https://opennmt.net/CTranslate2/installation.html to enable faster-whisper.

2. Add your OpenAI API key to environment variable OPENAI_API_KEY.

3. This project can be installed from PyPI:

   pip install openlrc
   

Usage

from openlrc import LRCer

lrcer = LRCer()
lrcer('./data/test.mp3')  # Generate ./data/test.lrc

Todo

• Add transcribed examples.
  • Song
  • Podcast
  • Audiobook
• Make translate prompt more robust.
• Add local LLM support.
• Multi-thead support for both whisper model and GPT request.
• Automatically fix json encoder error using GPT.

Credits

• https://github.com/guillaumekln/faster-whisper
• https://github.com/openai/openai-python
• https://github.com/openai/whisper