Dongchao

/

UniAudio2_ckpt

like 0

Hi! I'm Niels from the Hugging Face community science team. I've updated the model card for UniAudio 2.0 to include:

• Metadata for the audio-to-audio pipeline tag and the MIT license.
• Links to the research paper, project demo page, and official GitHub repository.
• A summary of supported tasks across speech, sound, and music.
• Sample usage instructions for both understanding (ASR) and generation (TTS) based on the official documentation.
• The BibTeX citation for the paper.