When translating a sequence of text files using Huggingface, the model is loaded multiple times

sillsdev / silnlp

A set of pipelines for performing experiments on various NLP tasks with a focus on resource-poor/minority languages.

Other

35 stars 3 forks source link

When translating a sequence of text files using Huggingface, the model is loaded multiple times #535

Open benjaminking opened 1 month ago

benjaminking commented 1 month ago

If you translate a sequence of text files using translate.py and "--start-seq", the model is loaded into memory multiple times. If you translate 10 files, the model will be loaded 10 times, which is inefficient.