README.md

• RUN

** BERT Language Model

python``` model_path = "/language-ml-lab/iranian-azerbaijani-nlp/AzerBert/checkpoint-11630" tokenizer_path = "/language-ml-lab/iranian-azerbaijani-nlp/AzerBert" fill_mask = pipeline("fill-mask", model=model_path, tokenizer=tokenizer_path)

example = "خارجدن یئمک گتیریلمهسینه امکان وئرمیردیلر [MASK]" arr_example = example.split(" ") result = fill_mask(example, arr_example)

for prediction in result: print("Predicted Word: ", prediction["token_str"]) print(f"Final sentence: {prediction['sequence']}, confidence: {prediction['score']}") ```