Finetuned T5 on the french part of Lang-8 to automatically correct sentences.
Since the Lang-8 dataset contains really short sentences, the model does not generalize well with sentences larger than 10 words.
I'll upload soon the cleaned dataset that I've used for training.
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Space using
PoloHuggingface/French_grammar_error_corrector1
