azuwis/pianotrans

Simple GUI for ByteDance's Piano Transcription with Pedals

What it solves

It provides a user-friendly graphical interface (GUI) and simplified installation for ByteDance's piano transcription system, which converts audio or video recordings of piano music into MIDI files that include pedal information.

How it works

The project acts as a wrapper and packaging tool for the "High-resolution Piano Transcription with Pedals" PyTorch implementation. It allows users to select audio or video files via a GUI or command line, then runs the underlying AI model to transcribe the notes and pedals into a MIDI format.

Who it’s for

Musicians, composers, and audio engineers who want to convert piano recordings to MIDI without needing to manually configure a Python environment or PyTorch dependencies.

Highlights

  • Cross-platform support: Available for Windows, Linux, and macOS.
  • Simplified installation: Offers pre-packaged binaries for Windows and Nix-based installation for Linux/macOS.
  • Batch processing: Supports selecting and transcribing multiple files simultaneously.
  • Hardware flexibility: Automatically uses GPU for inference but provides a CPU-only mode if needed.

Related

  • Project
    espressif/esp-sr

    A speech recognition framework for Espressif chips that enables offline wake word detection, voice command recognition, and audio preprocessing.

  • Project
    appleboy/CodeGPT

    CodeGPT is a Go‑based CLI that uses LLM APIs (OpenAI, Azure, Gemini, Anthropic, Ollama, Groq, OpenRouter) to automatically generate Conventional‑Commit messages and brief code‑review summaries. It can install a Git `prepare‑commit‑msg` hook, supports custom prompts, language translation, streaming output, and flexible configuration (API keys, providers, proxy, diff context, etc.). Installable via Homebrew, Chocolatey, script, binary, or `go install`.

  • Project
    kyutai-labs/hibiki

    Hibiki is a model for streaming speech-to-speech translation that generates natural target speech and text in real-time as the user speaks.

  • Project
    alchaincyf/huashu-skills

    A curated index of 53 Claude‑compatible *Agent Skills* (design, data, video, writing, persona‑based reasoning, etc.) with install instructions, an update checker, and a machine‑readable catalog. Enables AI agents to perform concrete productivity tasks without custom coding.