audio-preprocess
The audio-preprocess project delivers a suite of audio processing tools capable of converting video and audio files to WAV, separating vocals, performing automatic slicing, matching loudness, calculating audio length, and resampling. It offers transcription functionalities directly or via FunASR, along with data statistics support. The system is validated on Ubuntu platforms with Python, making it suitable for users seeking precision in audio handling. Features like WhisperX transcription are under development. User feedback is valued to drive ongoing improvements, ensuring the tool remains reliable and up-to-date.
