As we know python is not multi-threaded so entity extraction for a huge dataset containing 2.2k entities is taking almost 10 hours of training time. I am currently experimenting with multi-threading, multi-processing & overcoming GIL concepts. But so far no luck. Anyone here can help me with making CRFEntityExtractor into multi-threaded system ? Any suggestion is appreciated. Thank you.

All core usage in RASA

YoungXu06 (Young Xu) November 13, 2020, 12:52pm 5

hi akelad, could you please answer my question here, thanks advance!

Topic		Replies	Views
CRFEntityExtractor how much time take to complete Welcome to the Rasa Community Forum!	5	874	December 31, 2019
How to train CRFEntityExtractor faster? Rasa Open Source	3	849	December 20, 2019
Entity extraction training time exploded using roles for entitites Rasa Open Source	6	573	June 4, 2020
Entity tagging for large datasets Rasa Open Source	11	2814	May 17, 2019
Entity Extractors Comparison Rasa Open Source	2	389	October 18, 2021