Text-to-Audio
Transformers
PyTorch
musicgen

Faster MusicGen Generation with Streaming

#7
by sanchit-gandhi - opened

There's no need to wait for MusicGen to generate the full audio before you can start listening to the outputs ⏰ With streaming, you can play the audio as soon as the first chunk is ready 🎵 In practice, this reduces the latency to just 5s ⚡️

Check-out the demo: https://huggingface.co/spaces/sanchit-gandhi/musicgen-streaming

@sanchit-gandhi there seems to be an internal infra error in the provided demo

also confused about how to enable streaming using musicgen-medium?

image.png

Sign up or log in to comment