Audio
Models for speech processing, audio generation, and classification
Audio tasks work with sound and speech.
Speech Tasks
- Automatic Speech Recognition: Transcribe speech into text
- Text-to-Speech: Convert text into spoken audio
- Voice Activity Detection: Detect whether speech is present in audio
Audio Generation
- Text-to-Audio: Generate sounds or music from text
- Audio-to-Audio: Transform or enhance audio signals
Audio Understanding
- Audio Classification: Categorize audio clips