xfspell
xfspell copied to clipboard
mhagiwara
xfspell — the Transformer Spell Checker
While testing this model, I noticed several cases when the model **adds extra phrases or words** as shown in below example. Tbh, this makes the model quite risky for usage...
Hello, After running this command: ``` $ echo "tisimptant too spll chck ths dcment." \ | python src/tokenize.py \ | fairseq-interactive model7m/ \ --path model7m/checkpoint_best.pt \ --source-lang fr --target-lang en...
I download the model and deploy it in my server. In my tests, it takes **several seconds**(usually 1 - 3 s) to get the result for a sentence of a...
Result
I ran with an example: echo "In accordance wit a form she specifed." | python src/tokenize.py | fairseq-interactive model7m/ --path model7m/checkpoint_best.pt --source-lang en --target-lang en | python src/format_fairseq_output.py In accordance...
Thank you for sharing the model and the blog post, looks very interesting. Unfortunately, when running the example in a Python 3.7.5 virtual environment with installed requirements, I'm getting the...
Hi, super interesting work, and thanks for sharing! I'm wondering if you could include a training script in the repository that would allow one to train one's own model. :)...
I have a dataset of food item names and I want to train xfspell on my dataset. My doubt is how do I create .tok file? I do not see...
Hi, this is great and really interesting. Thanks for the great blog post. I have a large amount of misspelled input sentences. Is there a way of feeding them into...
RuntimeError: unexpected EOF, expected 1119993 more bytes. The file might be corrupted. This is the end sentence of the error i am getting when i try to use it here...
