openlrc 1.2.0

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 LLM, e.g. OpenAI-GPT, Anthropic-Claude.

New 🚨

• 2024.3.29: Claude models are now available for translation. According to the testing, Claude 3 Sonnet performs way better than GPT-3.5 Turbo. We recommend using Claude 3 Sonnet for non-english audio (source language) translation (For now, the default model are still GPT-3.5 Turbo):

  lrcer = LRCer(chatbot_model='claude-3-sonnet-20240229')
  

Installation ⚙️

1. Please install CUDA 11.x and cuDNN 8 for CUDA 11 first according to https://opennmt.net/CTranslate2/installation.html to enable faster-whisper.

   faster-whisper also needs cuBLAS for CUDA 11 installed.

   For Windows Users (click to expand)

   (For Windows Users only) Windows user can Download the libraries from Purfview's repository:

   Purfview's whisper-standalone-win provides the required NVIDIA libraries for Windows in a single archive. Decompress the archive and place the libraries in a directory included in the PATH.

2. Add LLM API keys, you can either:

   • Add your OpenAI API key to environment variable OPENAI_API_KEY.
   • Add your Anthropic API key to environment variable ANTHROPIC_API_KEY.

3. Install PyTorch:

   pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
   

4. Install latest fast-whisper

   pip install git+https://github.com/guillaumekln/faster-whisper
   

5. Install ffmpeg and add bin directory to your PATH.

6. 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

if __name__ == '__main__':
    lrcer = LRCer()

    # Single file
    lrcer.run('./data/test.mp3',
              target_lang='zh-cn')  # Generate translated ./data/test.lrc with default translate prompt.

    # Multiple files
    lrcer.run(['./data/test1.mp3', './data/test2.mp3'], target_lang='zh-cn')
    # Note we run the transcription sequentially, but run the translation concurrently for each file.

    # Path can contain video
    lrcer.run(['./data/test_audio.mp3', './data/test_video.mp4'], target_lang='zh-cn')
    # Generate translated ./data/test_audio.lrc and ./data/test_video.srt

    # Use context.yaml to improve translation
    lrcer.run('./data/test.mp3', target_lang='zh-cn', context_path='./data/context.yaml')

    # To skip translation process
    lrcer.run('./data/test.mp3', target_lang='en', skip_trans=True)

    # Change asr_options or vad_options, check openlrc.defaults for details
    vad_options = {"threshold": 0.1}
    lrcer = LRCer(vad_options=vad_options)
    lrcer.run('./data/test.mp3', target_lang='zh-cn')

    # Enhance the audio using noise suppression (consume more time).
    lrcer.run('./data/test.mp3', target_lang='zh-cn', noise_suppress=True)

    # Change the LLM model for translation
    lrcer = LRCer(chatbot_model='claude-3-sonnet-20240229')
    lrcer.run('./data/test.mp3', target_lang='zh-cn')

Check more details in Documentation.

Context

Utilize the available context to enhance the quality of your translation. Save them as context.yaml in the same directory as your audio file.

[!NOTE] The improvement of translation quality from Context is NOT guaranteed.

background: "This is a multi-line background.
This is a basic example."
audio_type: Movie
description_map: {
  movie_name1 (without extension): "This
  is a multi-line description for movie1.",
  movie_name2 (without extension): "This
  is a multi-line description for movie2.",
  movie_name3 (without extension): "This is a single-line description for movie 3.",
}

Pricing 💰

pricing data from OpenAI and Anthropic

Model Name	Pricing for 1M Tokens (Input/Output) (USD)	Cost for 1 Hour Audio (USD)
gpt-3.5-turbo-0125	0.5, 1.5	0.01
gpt-3.5-turbo	0.5, 1.5	0.01
gpt-4-0125-preview	10, 30	0.1
gpt-4-turbo-preview	10, 30	0.1
claude-3-haiku-20240307	0.25, 1.25	0.015
claude-3-sonnet-20240229	3, 15	0.2
claude-3-opus-20240229	15, 75	1

Note the cost is estimated based on the token count of the input and output text. The actual cost may vary due to the language and audio speed.

Recommended translation model

For english audio, we recommend using gpt-3.5-turbo.

For non-english audio, we recommend using claude-3-sonnet-20240229.

Todo

• [Efficiency] Batched translate/polish for GPT request (enable contextual ability).
• [Efficiency] Concurrent support for GPT request.
• [Translation Quality] Make translate prompt more robust according to https://github.com/openai/openai-cookbook.
• [Feature] Automatically fix json encoder error using GPT.
• [Efficiency] Asynchronously perform transcription and translation for multiple audio inputs.
• [Quality] Improve batched translation/polish prompt according to gpt-subtrans.
• [Feature] Input video support.
• [Feature] Multiple output format support.
• [Quality] Speech enhancement for input audio.
• [Feature] Preprocessor: Voice-music separation.
• [Feature] Align ground-truth transcription with audio.
• [Quality] Use multilingual language model to assess translation quality.
• [Efficiency] Add Azure OpenAI Service support.
• [Quality] Use claude for translation.
• [Feature] Add local LLM support.
• [Feature] Multiple translate engine (Anthropic, Microsoft, DeepL, Google, etc.) support.
• [Feature] Build a electron + fastapi GUI for cross-platform application.
• Add fine-tuned whisper-large-v2 models for common languages.
• [Others] Add transcribed examples.
  • Song
  • Podcast
  • Audiobook

Credits

• https://github.com/guillaumekln/faster-whisper
• https://github.com/m-bain/whisperX
• https://github.com/openai/openai-python
• https://github.com/openai/whisper
• https://github.com/machinewrapped/gpt-subtrans
• https://github.com/MicrosoftTranslator/Text-Translation-API-V3-Python

Star History