Transcribes piano audio and makes it into a cool video
😵 Uh oh! This model can't be run on Replicate because it was built with a version of Cog or Python that is no longer supported. If you are the owner of this model, consider updating it to use a recent version of Cog. If you need any help, please Contact us about it.
This model runs on Nvidia T4 GPU hardware. We don't yet have enough runs of this model to provide performance information.
Piano transcription model from High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times, Kong et al., 2021. Achieves 96.72% onset-F1 on the MAESTRO dataset.
Transcribes audio input to MIDI and re-renders a Synthesia-esque video from the transcription.
Github: bytedance/piano_transcription