You can deploy this model and start earning money today!

Ericizepic/
T5-Address_Std_v6

Name: T5-Address_Std_v6
Availability: InStock

transformers

safetensors

text2text-generation

Ericizepic/address_std_11

1910.09700

text-generation-inference

endpoints_compatible

Views

No views yet

Model Card for Model ID

Converts non standard canadian address to a standardized form. This includes correcting spelling/spacing errors as well as standardizing non standard abbreviations and terms.

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Eric Du
Finetuned from model [optional]: T5-small Transformer

Uses

Designed to correct addresses that are a result of OCR extractions. Useful in the following cases:

Non-Standard Address	Standard Address
734 audley road s ajax ontario	734 audley rd s ajax on
torontoonta	toronto on
#97 2978 range line road ca	unit 97 2978 range line rd ca

How to Get Started with the Model

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained(model_name)
model = T5ForConditionalGeneration.from_pretrained(model_name)

input_ids = tokenizer("58 abc street tronto ont.", return_tensors="pt").input_ids
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Ericizepic/T5-Address_Std_v6