speedyk-005

speedyk-005/yasbd-lib

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

3 stars 9 forks 3 watchers Python Mozilla Public License 2.0

good-first-issue help-wanted natural-language-processing nlp nlp-library python sbd sentence-boundary-detection sentence-segmentation sentence-splitter sentence-splitting text-processing

34 Open Issues Need Help Last updated: Jul 1, 2026

Open Issues Need Help

View All on GitHub

[feat] Expand SUFFIXES in hyphenated word finder about 6 hours ago

enhancement good first issue feature edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] StreamCleaner deletes /// slashes and glues words together about 10 hours ago

bug documentation good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[feat] Add line ending normalization to the default cleaning pipeline about 12 hours ago

enhancement good first issue feature edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[chore] Replace lambdas in DEFAULT_CLEANING_PIPELINE with named functions about 21 hours ago

good first issue refactor chore

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[chore] Combine same-module imports in __init__.py about 22 hours ago

good first issue refactor chore

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[feat] Add line ending normalization to the default cleaning pipeline 1 day ago

enhancement good first issue feature

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[chore] Replace manual adjacent boundary iteration with `itertools.pairwise` 7 days ago

good first issue refactor chore

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

🔒 Core Languages Locked at 39 (No new languages will be added) 15 days ago

documentation good first issue

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] Flattened list segmentation broken when there is a lot 15 days ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] `.\n` produces double boundary in detect() 15 days ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[chore] Merge "Pronouns & Demonstratives" into "Pronouns" 19 days ago

enhancement good first issue chore

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[feat] Add Armenian (hy) language support before language locking 20 days ago

good first issue feature language-request

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[style] Simplify `__eq__` attribute checks using `all()` 20 days ago

enhancement good first issue refactor

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[chore] remove unused `timeout` param from `_create_external_cleaner` 20 days ago

enhancement good first issue chore

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

Add more languages to reach 39 and lock new additions 20 days ago

help wanted feature language-request

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[docs] Add README to src/yasbd/rules/ with language family table 21 days ago

documentation good first issue

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[docs] Typos found in documentation 21 days ago

documentation good first issue

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] Missing commas in set literals cause silent string concatenation 22 days ago

bug good first issue

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] Flattened list heuristic is too permissive 23 days ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

🌍 Help Add More Languages to Yasbd 23 days ago

help wanted feature language-request

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] French 'est' blocks sentence boundary (inline abbreviation clash) 23 days ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[Inconsistencies] Some language rules replace base sets instead of extending them 28 days ago

bug good first issue refactor

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] Inherited German ordinal rule breaks sentence segmentation about 1 month ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] Com. & Adm. is incorrectly split into two sentences about 1 month ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[refactor] Remove implicit --lang default from CLI for API consistency about 1 month ago

enhancement good first issue refactor

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] Geographic coordinate directions (N., S., E., W.) treated as non-breaking abbreviations about 1 month ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

Rename REPORTING_VERBS to REPORTING_WORDS in my.py and th.py about 1 month ago

bug good first issue

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[feat] optional normalize_lang() utility (ISO-639-1 only) about 1 month ago

good first issue feature

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[enhancement] collapse newlines between sentences in StreamCleaner about 2 months ago

enhancement good first issue

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[feat] Add German (de) language support to Yasbd sentence splitter 2 months ago

help wanted feature new-language(s)

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] incorrect segmentation of single-letter markers within sentences 2 months ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[feat] add batch support for zh, ar, ru, pt languages in sentence splitter 2 months ago

help wanted feature new-language(s)

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] Incorrect Sentence Split on “a.m./p.m. + Date Abbreviation” 2 months ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing

[bug] reference abbreviations followed by square bracket incorrectly trigger sentence split 2 months ago

bug good first issue edge-cases

speedyk-005/yasbd-lib

3

Yabsd: A high-accuracy, from-scratch Sentence Boundary Detector (SBD) for production pipelines. Features a drop-in adapter for pysbd to fix edges cases without heavy refactoring.

Python

#good-first-issue#help-wanted#natural-language-processing#nlp#nlp-library#python#sbd#sentence-boundary-detection#sentence-segmentation#sentence-splitter#sentence-splitting#text-processing