Post
1977
π’ So far I noticed that π§ reasoning with llm π€ in English is tend to be more accurate than in other languages.
However, besides the GoogleTrans and other open transparent translators, I could not find one that could be easy to use solutions to avoid:
1.π΄ Third-party framework installation
2.π΄ Text chunking
3.π΄ support of meta-annotation like spans / objects / etc.
π To cope problem of IR from non-english texts, I am happy to share the bulk-translate 0.25.0. π
β https://github.com/nicolay-r/bulk-translate
bulk-translate is a tiny Python π no-string framework that allows translate series of texts with the pre-annotated fixed-spans that are invariant for translator.
It supports π¨βπ» API for quick data translation with (optionaly) annotated objects in texts (see figure below) in Python π
I make it accessible as much as possible for RAG and / or LLM-powered app downstreams:
π https://github.com/nicolay-r/bulk-translate/wiki
All you have to do is to provide iterator of texts, where each text:
1. β String object
2. β List of strings and nested lists that represent spans (value + any ID data).
π€ By default I provide a wrapper over googletrans which you can override with your own π₯
https://github.com/nicolay-r/bulk-translate/blob/master/models/googletrans_310a.py
However, besides the GoogleTrans and other open transparent translators, I could not find one that could be easy to use solutions to avoid:
1.π΄ Third-party framework installation
2.π΄ Text chunking
3.π΄ support of meta-annotation like spans / objects / etc.
π To cope problem of IR from non-english texts, I am happy to share the bulk-translate 0.25.0. π
β https://github.com/nicolay-r/bulk-translate
bulk-translate is a tiny Python π no-string framework that allows translate series of texts with the pre-annotated fixed-spans that are invariant for translator.
It supports π¨βπ» API for quick data translation with (optionaly) annotated objects in texts (see figure below) in Python π
I make it accessible as much as possible for RAG and / or LLM-powered app downstreams:
π https://github.com/nicolay-r/bulk-translate/wiki
All you have to do is to provide iterator of texts, where each text:
1. β String object
2. β List of strings and nested lists that represent spans (value + any ID data).
π€ By default I provide a wrapper over googletrans which you can override with your own π₯
https://github.com/nicolay-r/bulk-translate/blob/master/models/googletrans_310a.py