Skip to content

Tamil TN Cardinal Semiotic Class - #449

Open
surendran-246 wants to merge 46 commits into
NVIDIA:staging/tamil_tn_v1from
surendran-246:feat-ta-cardinal
Open

Tamil TN Cardinal Semiotic Class#449
surendran-246 wants to merge 46 commits into
NVIDIA:staging/tamil_tn_v1from
surendran-246:feat-ta-cardinal

Conversation

@surendran-246

@surendran-246 surendran-246 commented Jul 7, 2026

Copy link
Copy Markdown

What does this PR do ?

Add a one line overview of what this PR aims to accomplish.

Before your PR is "Ready for review"

Pre checks:

  • Have you signed your commits? Use git commit -s to sign.
  • Do all unittests finish successfully before sending PR?
    1. pytest or (if your machine does not have GPU) pytest --cpu from the root folder (given you marked your test cases accordingly @pytest.mark.run_only_on('CPU')).
    2. Sparrowhawk tests bash tools/text_processing_deployment/export_grammars.sh --MODE=test ...
  • If you are adding a new feature: Have you added test cases for both pytest and Sparrowhawk here.
  • Have you added __init__.py for every folder and subfolder, including data folder which has .TSV files?
  • Have you followed codeQL results and removed unused variables and imports (report is at the bottom of the PR in github review box) ?
  • Have you added the correct license header Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. to all newly added Python files?
  • If you copied nemo_text_processing/text_normalization/en/graph_utils.py your header's second line should be Copyright 2015 and onwards Google, Inc.. See an example here.
  • Remove import guards (try import: ... except: ...) if not already done.
  • If you added a new language or a new feature please update the NeMo documentation (lives in different repo).
  • Have you added your language support to tools/text_processing_deployment/pynini_export.py.

PR Type:

  • New Feature
  • Bugfix
  • Documentation
  • Test

If you haven't finished some of the above items you can still open "Draft" PR.

surendran-246 and others added 10 commits July 7, 2026 13:51
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
for more information, see https://pre-commit.ci

Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
@surendran-246 surendran-246 changed the title Tamil language cardinal semiotic class Tamil TN Cardinal Semiotic Class Jul 7, 2026
@surendran-246
surendran-246 marked this pull request as ready for review July 7, 2026 10:50
surendran-246 and others added 6 commits July 8, 2026 11:04
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
@github-actions

Copy link
Copy Markdown

This PR is stale because it has been open for 14 days with no activity. Remove stale label or comment or update or this will be closed in 7 days.

@github-actions github-actions Bot added the Stale label Jul 23, 2026
Signed-off-by: surendran-246 <surendrans@nvidia.com>
surendran-246 and others added 2 commits July 23, 2026 18:44
@github-actions github-actions Bot removed the Stale label Jul 24, 2026
Signed-off-by: surendran-246 <surendrans@nvidia.com>
@github-actions

github-actions Bot commented Aug 8, 2026

Copy link
Copy Markdown

This PR is stale because it has been open for 14 days with no activity. Remove stale label or comment or update or this will be closed in 7 days.

surendran-246 and others added 4 commits September 3, 2026 17:33
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Comment thread tests/nemo_text_processing/ta/test_sparrowhawk_normalization.sh Outdated
Signed-off-by: surendran-246 <surendrans@nvidia.com>
@surendran-246
surendran-246 requested a review from mgrafu September 7, 2026 05:01
Comment thread nemo_text_processing/text_normalization/ta/taggers/cardinal.py
Comment thread nemo_text_processing/text_normalization/ta/verbalizers/cardinal.py Outdated
Comment thread Jenkinsfile
Comment thread tests/nemo_text_processing/ta/__init__.py
surendran-246 and others added 2 commits September 9, 2026 14:29
Signed-off-by: surendran-246 <surendrans@nvidia.com>
@surendran-246
surendran-246 requested a review from mgrafu September 9, 2026 09:17
@surendran-246

surendran-246 commented Sep 9, 2026

Copy link
Copy Markdown
Author

Hi @mgrafu, Thanks for the review. I've addressed all the review comments. On the teens_and_ties.tsv line count: from my side I can only see 68 lines (10–19 + X0/X1/X2 for each of the 8 tens digits, not 90 lines. Attaching the file link below for reference:
[https://github.com/surendran-246/NeMo-text-processing/blob/0b2e12aee09f79eb48fedbe97bce422265910827/nemo_text_processing/text_normalization/ta/data/numbers/teens_and_ties.tsv].

Testing:

Cardinal, word, and punctuation pytest cases passed
Sparrowhawk testTNCardinal, testTNWord, and testTNPunctuation passed

surendran-246 and others added 3 commits September 9, 2026 16:00
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Comment thread nemo_text_processing/text_normalization/ta/verbalizers/cardinal.py Outdated
Comment thread tests/nemo_text_processing/ta/data_text_normalization/test_cases_punctuation.txt Outdated
Comment thread tests/nemo_text_processing/ta/data_text_normalization/test_cases_word.txt Outdated
௦௭௩~சுழியம் ஏழு மூன்று
0001~சுழியம் சுழியம் சுழியம் ஒன்று
௦௦௦~சுழியம் சுழியம் சுழியம்
10000~பத்துஆயிரம்

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is this spelling correct?

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes

100000000000~பத்துஆயிரம் கோடி
800~எட்டுநூறு
850~எட்டுநூற்று ஐம்பது
900~ஒன்பதுநூறு

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is this spelling correct?

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes

900~ஒன்பதுநூறு
905~ஒன்பதுநூற்று ஐந்து
987~ஒன்பதுநூற்று எண்பத்திஏழு
25~இருபத்திஐந்து

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is this spelling correct?

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why are all three spelled differently here? https://www.softschools.com/languages/tamil/tamil_numbers_1_100/

surendran-246 and others added 3 commits September 10, 2026 14:03
Signed-off-by: surendran-246 <surendrans@nvidia.com>
Signed-off-by: surendran-246 <surendrans@nvidia.com>
@surendran-246

surendran-246 commented Sep 10, 2026

Copy link
Copy Markdown
Author

Hi @mgrafu, thanks for the review! I've addressed all the review comments — updated the cardinal.py verbalizer docstring to reflect the actual tagger output, and reformatted test_cases_punctuation.txt and test_cases_word.txt to follow the English test case style. I also double-checked the spellings you flagged in test_cases_cardinal.txt, and they're correct as is.

Testing:
Cardinal, word, and punctuation pytest cases passed
Sparrowhawk testTNCardinal, testTNWord, and testTNPunctuation passed

(3–7) மற்றும் (10–15)~(மூன்று – ஏழு) மற்றும் (பத்து – பதினைந்து)
11;12;13~பதினொன்று;பன்னிரண்டு;பதிமூன்று
கோட்: "3"~கோட்: "மூன்று"
(20)வணக்கம்~(20)வணக்கம்

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why is the number not normalized here?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants