Error: You need to have sentencepiece installed to convert a slow tokenizer to a fast one.

PrithivirajDamodaran / Parrot_Paraphraser

A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational engines. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

Apache License 2.0

867 stars 143 forks source link

Error: You need to have sentencepiece installed to convert a slow tokenizer to a fast one. #5

Closed RahulBhasin closed 3 years ago

RahulBhasin commented 3 years ago

Hi,

I am facing the error pasted below: Capture

I already have 'sentencepiece' installed. I also tried using 'use_fast=False' flag in parrot.py file (pasted below), as suggested in many other discussions for the resolution of this error. Capture1

However, I am still facing this issue. Can you please help me to resolve it?

Thanks, Rahul

PrithivirajDamodaran commented 3 years ago

Not able to reproduce this issue.