# `Mx.Transcriber`
[🔗](https://github.com/mx-music/mx/blob/main/lib/mx/transcriber.ex#L1)

Transcribes images of single systems of printed music to ABC notation with a vision-language model, which `Mx.ABC` turns into a score.

The model is rokot-omr-2b from Hugging Face by default, or the Hugging Face id or local folder named in the `MX_TRANSCRIBER_MODEL` environment variable.
It runs in Python inside this OS process, through Pythonx: the first run installs Python, PyTorch and transformers with uv, and downloads the model into the Hugging Face cache.

# `transcribe`

The ABC text of each system image, in order, as `{:ok, [abc]}` or `{:error, message}`.

# `width`

The width in pixels to give each system, about 1400 as the model card of rokot-omr-2b asks.

---

*Consult [api-reference.md](api-reference.md) for complete listing*