XML documents translated in place, ALTO pages and AMČR metadata
in-place translation of ALTO / AMCR XML
In-place translation of XML (ALTO/AMCR) files into English, preserving every tag, namespace and coordinate.
Protected translation. A terminal branch — its output is recorded, not consumed.
- python3.11
- APILINDAT Translation
- APIUDPipe 2
- 🤗 HFfasttext-langID
- SSH OMPCizIUW
- licenseMIT
- funded byATRIUM
Where this sits in the pipeline
- page-classification
- →
- ocr-postprocess
- →
- translator
- →
- nlp-enrich
- →
- keyword-extract
- →
- digital-convert