Feat te itn stretch goals

[jaya-TN]

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.

[mayuris-00]

Core task is signed off - all 28 core cases pass and are correct.
Stretch goals (optional): all three attempted, which is commendable. Main follow-ups: complete and linguistically verify the hundreds (ideally via composition), and add matching tests.
Cleanup: remove the unnecessary inline # comments in the tagger and verbalizer.

[mayuris-00]

Correctly left empty as a package marker, per Section 5. No action required.

[mayuris-00]

Correctly left empty as a package marker, per Section 5. No action required.

[mayuris-00]

Status: Approved.

0 → సున్న matches the spec; native 0 → ౦ correctly added for the stretch goal.

[mayuris-00]

Status: Approved. All eighteen rows (10–20 and round tens) match the spec spellings exactly. No action required.

[mayuris-00]

Rows 1–9 match the spec spellings exactly.
Native Telugu numerals (౧–౯) are correctly added as additional rows mapping to the same digits — this satisfies stretch goal 3. No action required.

[mayuris-00]

Status: Approved; minor cleanup.

-TODO 3 is implemented correctly: pynini.closure(NEMO_NOT_QUOTE, 1) correctly captures the digit value between the quotes, and the token deletion logic is correct.
-Remove the inline comment. # Keep digits between quotes (1+ non-quote chars) just restates the line below it. Please delete it.

[mayuris-00]

Coverage is complete - all 72 compound values (21–29, 31–39, …, 91–99) are present, space-joined as the brief describes. Correct output.

[mayuris-00]

Status: Incomplete - primary item to address.

-Coverage gaps: the file enumerates 100–120, then mostly only X00–X10 per hundred (with a fuller 900 block and 999). Values such as 156, 372, 467, 543, 678 are absent and will be silently rejected.
-Linguistic accuracy: the combining form is questionable. Standard Telugu uses నూట before a remainder (101 = నూట ఒకటి, 110 = నూట పది) and the plural వందల(ు) (200 = రెండు వందలు, 201 = రెండు వందల ఒకటి), not వంద ఒకటి.
Recommendation: replace this file with a composed hundreds rule, which resolves both the coverage gaps and the surface-form consistency in one place.

[mayuris-00]

Matches the spec's checker script and the required root location. No action required.

[mayuris-00]

Status: Core approved; stretch coverage insufficient.

The 28 core cases match Section 8 exactly and use the correct input~expected format.
Stretch testing is thin: ~6 stretch cases were added for 250+ added entries. Section 9 requires a matching test line for every stretch number added; the missing hundreds (e.g. 156, 372, 543) were never tested, which is why the coverage gaps went unnoticed. Please add representative tests across the hundreds range.