openlrc 0.1.0

Transcribe (whisper) and translate (gpt) voice into LRC file.

Open-Lyrics

Open-Lyrics is a Python library that transcribes voice files using faster-whisper, and translates/polishes the resulting text into .lrc files in the desired language using OpenAI-GPT.

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. Install whisperx

   pip install git+https://github.com/m-bain/whisperx.git
   

4. This project can be installed from PyPI:

   pip install openlrc
   

   or install directly from GitHub:

   pip install git+https://github.com/zh-plus/Open-Lyrics
   

Usage

from openlrc import LRCer

lrcer = LRCer()
lrcer('./data/test.mp3', target_lang='zh-cn')  # Generate translated ./data/test.lrc with default translate prompt.
# lrcer('./data/test.mp3', prompter='lovely_trans')  # Generate ./data/test.lrc with lovely colloquial expressions.

Todo

• Batched translate/polish for GPT request (enable contextual ability).
• Concurrent support for GPT request.
• Use whisperx for transcription.
• Make translate prompt more robust according to https://github.com/openai/openai-cookbook.
• Automatically fix json encoder error using GPT.
• Multiple output format support.
• Add Azure OpenAI Service support.
• Add local LLM support.
• Add transcribed examples.
  • Song
  • Podcast
  • Audiobook

Credits

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