Generate drum patterns from audio
Generate audio from text using a prompt
Chinese (Taiwan) Automatic Speech Recognition.
Align audio with text to get timestamps
MP-SENet is a speech enhancement model.
Turn audio into modified vocals with background
Enhance audio quality with AudioSR
HuggingFace Space for https://github.com/seiichiinoue/odcnn
Grade essays for IELTS and general English
Separate vocals from background in audio
Generate speaker-specific clips from a video
Visualizing Audio Features.