Spaces:

Didier
/

Postal_address_canada_parsing

Sleeping

Didier commited on Aug 14, 2024

Commit

a08b56f

verified ·

1 Parent(s): 3a6ee9e

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -84,7 +84,7 @@ with gr.Blocks() as demo:
             - **Labels (address components)**:
                 - O, STREET_NB, STREET_NAME, UNIT, CITY, REGION, POSTCODE
             - Dataset trained on:
-                - Approx. 1 million Canadian postal addresses from OpenAddresses.io
             - (Current) Limitations:
                 - no label for person_name / company_name (no data to train on)
                 - trained on **post-normalized** addresses from OpenAddresses.io,

             - **Labels (address components)**:
                 - O, STREET_NB, STREET_NAME, UNIT, CITY, REGION, POSTCODE
             - Dataset trained on:
+                - Random sample of 1 million Canadian postal addresses out of the 16+ million addresses available at OpenAddresses.io
             - (Current) Limitations:
                 - no label for person_name / company_name (no data to train on)
                 - trained on **post-normalized** addresses from OpenAddresses.io,