bytedance/piano_transcription

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

2021 stars · 259 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of ByteDance's high-resolution piano transcription system that converts piano audio recordings into MIDI files. It includes a pretrained model for inference and training code based on the MAESTRO dataset.

Use cases

• convert piano recordings to MIDI files
• transcribe piano audio into note events
• train a piano transcription model from scratch
• extract MIDI from piano performance audio
• run audio-to-MIDI transcription on GPU

When to choose

• you need to transcribe solo piano recordings into MIDI
• you want a pretrained high-resolution transcription model
• you want to reproduce or extend research on piano transcription

When to avoid

• you need transcription of non-piano instruments or polyphonic general music
• you need an actively maintained project with recent updates
• you need a production service without any ML setup

Facets

library · maturity maintenance

machine-learning audio-processing deep-learning machine-learning python cli pytorch piano-transcription audio-to-midi pretrained-model music-transcription audio music-information-retrieval gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="bytedance/piano_transcription")