datasets==1.16.1 en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.3.1/en_core_web_sm-2.3.1.tar.gz numpy==1.22.0 sentencepiece==0.1.96 spacy tokenizers==0.10.3 torch==1.7.1 transformers==4.12.5 gradio pymupdf