-
Notifications
You must be signed in to change notification settings - Fork 5
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update: fixing bug raised around stanza model not having certain words in vocabulary, along with efforts to improve latency #115
base: master
Are you sure you want to change the base?
Conversation
Sentry link for the bug |
… replacing with fuzzy search
Added fuzzy search, using |
Codecov Report
@@ Coverage Diff @@
## master #115 +/- ##
=========================================
Coverage 100.00% 100.00%
=========================================
Files 47 47
Lines 1921 1925 +4
=========================================
+ Hits 1921 1925 +4
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
""" | ||
value = value + str(word.text) + " " | ||
if value != "": | ||
matches = process.extract(value, entity_patterns) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Make it a flag to get all entities or 1 entity
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
use pyinstrument for profiling the changes and speed gains
…e which was happening earlier
…and switched to extractOne method in fuzzy searching
…and switched to extractOne method in fuzzy searching, and updating type check Signed-off-by: Achintya Shankhdhar <[email protected]>
6534fb1
to
85fa241
Compare
…and switched to extractOne method in fuzzy searching, and updating type check, adding PatternList Signed-off-by: Achintya Shankhdhar <[email protected]>
85fa241
to
7bcd692
Compare
…and switched to extractOne method in fuzzy searching, and updating type check, adding PatternList
ebffdfa
to
5f836e5
Compare
A bug was found when testing in Oppo when users are saying something in Hindi but English ASR is used. certain words are out of vocabulary for the stanza model.
the PR is a error handling for this instance