Faster MusicGen Generation with Streaming
#13
by
sanchit-gandhi
HF staff
- 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
Hey man, Currently i am facing a problem of concurrent inferencing with streamer on... So, when i increase the concurrent request to 3 different Music gen models the generation time of each increases. solution from you will be great...!
-Thanks