Kyle's picture

Kyle PRO

iky1e

AI & ML interests

None yet

Recent Activity

updated a collection 1 day ago
Interesting LLM Models
liked a model 1 day ago
Xkev/Llama-3.2V-11B-cot
updated a collection 1 day ago
Open Datasets
View all activity

Organizations

None yet

iky1e's activity

reacted to nicolay-r's post with šŸ‘€ 1 day ago
view post
Post
2148
šŸ“¢ So far I noticed that šŸ§  reasoning with llm šŸ¤– 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.šŸ”“ Third-party framework installation
2.šŸ”“ Text chunking
3.šŸ”“ support of meta-annotation like spans / objects / etc.

šŸ’Ž To cope problem of IR from non-english texts, I am happy to share the bulk-translate 0.25.0. šŸŽŠ

ā­ https://github.com/nicolay-r/bulk-translate

bulk-translate is a tiny Python šŸ no-string framework that allows translate series of texts with the pre-annotated fixed-spans that are invariant for translator.

It supports šŸ‘Øā€šŸ’» API for quick data translation with (optionaly) annotated objects in texts (see figure below) in Python šŸ
I make it accessible as much as possible for RAG and / or LLM-powered app downstreams:
šŸ“˜ https://github.com/nicolay-r/bulk-translate/wiki

All you have to do is to provide iterator of texts, where each text:
1. āœ… String object
2. āœ… List of strings and nested lists that represent spans (value + any ID data).

šŸ¤– By default I provide a wrapper over googletrans which you can override with your own šŸ”„
https://github.com/nicolay-r/bulk-translate/blob/master/models/googletrans_310a.py