khmerns 0.0.3__tar.gz

khmerns-0.0.3/.github/workflows/wheels.yml

@@ -0,0 +1,93 @@
+name: Wheels
+
+on:
+  workflow_dispatch:
+  pull_request:
+  push:
+    branches:
+      - main
+  release:
+    types:
+      - published
+
+env:
+  FORCE_COLOR: 3
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build_sdist:
+    name: Build SDist
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v5
+        with:
+          submodules: true
+
+      - name: Build SDist
+        run: pipx run build --sdist
+
+      - name: Check metadata
+        run: pipx run twine check dist/*
+
+      - uses: actions/upload-artifact@v5
+        with:
+          name: cibw-sdist
+          path: dist/*.tar.gz
+
+  build_wheels:
+    name: Wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, macos-15-intel, windows-latest, ubuntu-24.04-arm]
+    env:
+      MACOSX_DEPLOYMENT_TARGET: "11.0"
+    steps:
+      - uses: actions/checkout@v5
+        with:
+          submodules: true
+
+      - uses: astral-sh/setup-uv@v7
+
+      - uses: pypa/cibuildwheel@v3.3
+
+      - name: Verify clean directory
+        run: git diff --exit-code
+        shell: bash
+
+      - uses: actions/upload-artifact@v5
+        with:
+          name: cibw-wheels-${{ matrix.os }}
+          path: wheelhouse/*.whl
+
+  upload_all:
+    name: Upload if release
+    needs: [build_wheels, build_sdist]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'release' && github.event.action == 'published'
+    environment: pypi
+    permissions:
+      id-token: write
+      attestations: write
+
+    steps:
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.x"
+
+      - uses: actions/download-artifact@v6
+        with:
+          pattern: cibw-*
+          merge-multiple: true
+          path: dist
+
+      - name: Generate artifact attestation for sdist and wheels
+        uses: actions/attest-build-provenance@v3
+        with:
+          subject-path: "dist/*"
+
+      - uses: pypa/gh-action-pypi-publish@release/v1

khmerns-0.0.3/.gitignore

@@ -0,0 +1,248 @@
+# General
+.DS_Store
+__MACOSX/
+.AppleDouble
+.LSOverride
+Icon[
+]
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+data/
+assets
+.claude
+training/CLAUDE.md
+CLAUDE.md

khmerns-0.0.3/CMakeLists.txt

@@ -0,0 +1,56 @@
+# Require CMake 3.15+ (matching scikit-build-core)
+cmake_minimum_required(VERSION 3.15...4.0)
+
+# Scikit-build-core sets these values
+project(
+  ${SKBUILD_PROJECT_NAME}
+  VERSION ${SKBUILD_PROJECT_VERSION}
+  LANGUAGES C CXX)
+
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
+  set(CMAKE_BUILD_TYPE Release CACHE STRING "Build type" FORCE)
+endif()
+
+# Find pybind11 and Python
+find_package(pybind11 CONFIG REQUIRED)
+
+# ===== Fetch GGML Library =====
+include(FetchContent)
+FetchContent_Declare(
+  ggml
+  GIT_REPOSITORY https://github.com/ggerganov/ggml.git
+  GIT_TAG        a8db410a252c8c8f2d120c6f2e7133ebe032f35d
+)
+set(GGML_BUILD_EXAMPLES OFF CACHE BOOL "" FORCE)
+set(GGML_BUILD_TESTS OFF CACHE BOOL "" FORCE)
+set(GGML_STATIC ON CACHE BOOL "" FORCE)
+set(BUILD_SHARED_LIBS OFF CACHE BOOL "" FORCE)
+FetchContent_MakeAvailable(ggml)
+
+# ===== Create Python Module =====
+python_add_library(_core MODULE
+  src/main.cpp
+  src/tokenizer.cpp
+  src/crf.cpp
+  src/khmer-segmenter.cpp
+  WITH_SOABI
+)
+
+target_include_directories(_core PRIVATE
+  ${CMAKE_CURRENT_SOURCE_DIR}/src
+)
+
+target_link_libraries(_core PRIVATE
+  pybind11::headers
+  ggml
+)
+
+# Pass version info
+target_compile_definitions(_core PRIVATE VERSION_INFO="${PROJECT_VERSION}")
+
+# Install to the khmerns package directory
+install(TARGETS _core DESTINATION khmerns)

khmerns-0.0.3/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Seanghay Yath
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

khmerns-0.0.3/PKG-INFO

@@ -0,0 +1,121 @@
+Metadata-Version: 2.4
+Name: khmerns
+Version: 0.0.3
+Summary: Khmer Neural Segmenter
+Keywords: khmer,nlp,segmentation,tokenization,neural-network
+Author-Email: Seanghay Yath <seanghay.dev@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Project-URL: Homepage, https://github.com/seanghay/khmer-neural-segmenter
+Project-URL: Repository, https://github.com/seanghay/khmer-neural-segmenter
+Project-URL: Issues, https://github.com/seanghay/khmer-neural-segmenter/issues
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+
+# Khmer Neural Segmenter
+
+A fast Khmer word segmentation library.
+
+<img src="img/graph.png" alt="" width=500>
+
+## Installation
+
+```
+pip install khmerns
+```
+
+## Usage
+
+```python
+from khmerns import tokenize
+
+# Returns a list of words
+words = tokenize("សួស្តីបងប្អូន")
+# ['សួស្តី', 'បង', 'ប្អូន']
+```
+
+You can also use the class-based API if you prefer:
+
+```python
+from khmerns import KhmerSegmenter
+
+segmenter = KhmerSegmenter()
+words = segmenter.tokenize("សួស្តីបងប្អូន")
+# or
+words = segmenter("សួស្តីបងប្អូន")
+```
+
+## Training
+
+The training pipeline lives in the `training/` directory. It trains a BiGRU + CRF model on character-level BIO tags, then converts the result to GGUF for the C++ inference backend.
+
+### Data format
+
+Training data is a plain text file at `training/data/train.txt`. One word per line. Words that appear on consecutive lines are treated as part of the same sentence. The model learns word boundaries from this.
+
+Example `training/data/train.txt`:
+
+```
+សួស្តី
+បង
+ប្អូន
+ខ្ញុំ
+ទៅ
+ផ្សារ
+```
+
+Non-Khmer tokens (spaces, punctuation, numbers, Latin text) are tagged as `NON-KHMER`. Khmer tokens get `B-WORD` on the first character and `I-WORD` on the rest.
+
+### Steps
+
+```bash
+cd training
+pip install -r requirements.txt
+```
+
+**1. Prepare training data**
+
+Place your segmented text in `data/train.txt` (one word per line). If you have raw unsegmented Khmer text, you can use the generation script to pre-segment it:
+
+```bash
+python generate.py
+```
+
+This requires `khmersegment` and a source text file. Edit the path in `generate.py` to point to your raw text.
+
+**2. Train**
+
+```bash
+python train.py
+```
+
+Trains for 20 epochs with AdamW (lr=1e-5) and ReduceLROnPlateau. Saves `best_model.pt` (best eval loss) and `model.pt` (final). Uses CUDA if available.
+
+**3. Convert to GGUF**
+
+```bash
+python convert_to_gguf.py best_model.pt model.gguf
+```
+
+This produces a GGUF file (~3.3MB) containing all model weights.
+
+**4. Embed in the C++ binary**
+
+To use the new model in the library, convert the GGUF file to a C header and replace `src/model_data.h`, then rebuild:
+
+```bash
+xxd -i model.gguf > ../src/model_data.h
+pip install -e ..
+```
+
+## License
+
+MIT

khmerns-0.0.3/README.md

@@ -0,0 +1,99 @@
+# Khmer Neural Segmenter
+
+A fast Khmer word segmentation library.
+
+<img src="img/graph.png" alt="" width=500>
+
+## Installation
+
+```
+pip install khmerns
+```
+
+## Usage
+
+```python
+from khmerns import tokenize
+
+# Returns a list of words
+words = tokenize("សួស្តីបងប្អូន")
+# ['សួស្តី', 'បង', 'ប្អូន']
+```
+
+You can also use the class-based API if you prefer:
+
+```python
+from khmerns import KhmerSegmenter
+
+segmenter = KhmerSegmenter()
+words = segmenter.tokenize("សួស្តីបងប្អូន")
+# or
+words = segmenter("សួស្តីបងប្អូន")
+```
+
+## Training
+
+The training pipeline lives in the `training/` directory. It trains a BiGRU + CRF model on character-level BIO tags, then converts the result to GGUF for the C++ inference backend.
+
+### Data format
+
+Training data is a plain text file at `training/data/train.txt`. One word per line. Words that appear on consecutive lines are treated as part of the same sentence. The model learns word boundaries from this.
+
+Example `training/data/train.txt`:
+
+```
+សួស្តី
+បង
+ប្អូន
+ខ្ញុំ
+ទៅ
+ផ្សារ
+```
+
+Non-Khmer tokens (spaces, punctuation, numbers, Latin text) are tagged as `NON-KHMER`. Khmer tokens get `B-WORD` on the first character and `I-WORD` on the rest.
+
+### Steps
+
+```bash
+cd training
+pip install -r requirements.txt
+```
+
+**1. Prepare training data**
+
+Place your segmented text in `data/train.txt` (one word per line). If you have raw unsegmented Khmer text, you can use the generation script to pre-segment it:
+
+```bash
+python generate.py
+```
+
+This requires `khmersegment` and a source text file. Edit the path in `generate.py` to point to your raw text.
+
+**2. Train**
+
+```bash
+python train.py
+```
+
+Trains for 20 epochs with AdamW (lr=1e-5) and ReduceLROnPlateau. Saves `best_model.pt` (best eval loss) and `model.pt` (final). Uses CUDA if available.
+
+**3. Convert to GGUF**
+
+```bash
+python convert_to_gguf.py best_model.pt model.gguf
+```
+
+This produces a GGUF file (~3.3MB) containing all model weights.
+
+**4. Embed in the C++ binary**
+
+To use the new model in the library, convert the GGUF file to a C header and replace `src/model_data.h`, then rebuild:
+
+```bash
+xxd -i model.gguf > ../src/model_data.h
+pip install -e ..
+```
+
+## License
+
+MIT

khmerns-0.0.3/pyproject.toml

@@ -0,0 +1,51 @@
+[build-system]
+requires = ["scikit-build-core>=0.11", "pybind11>=3.0"]
+build-backend = "scikit_build_core.build"
+
+[project]
+name = "khmerns"
+version = "0.0.3"
+license = "MIT"
+license-files = ["LICENSE"]
+description = "Khmer Neural Segmenter"
+readme = "README.md"
+authors = [{ name = "Seanghay Yath", email = "seanghay.dev@gmail.com" }]
+requires-python = ">=3.9"
+keywords = ["khmer", "nlp", "segmentation", "tokenization", "neural-network"]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
+]
+
+[project.urls]
+Homepage = "https://github.com/seanghay/khmer-neural-segmenter"
+Repository = "https://github.com/seanghay/khmer-neural-segmenter"
+Issues = "https://github.com/seanghay/khmer-neural-segmenter/issues"
+
+[tool.scikit-build]
+minimum-version = "build-system.requires"
+wheel.packages = ["src/khmerns"]
+
+[tool.cibuildwheel]
+build-frontend = "build[uv]"
+enable = ["pypy"]
+
+[tool.cibuildwheel.pyodide]
+build-frontend = { name = "build", args = ["--exports", "whole_archive"] }
+
+[tool.cibuildwheel.ios]
+build-frontend = "build"
+xbuild-tools = ["cmake", "ninja"]
+
+[tool.cibuildwheel.android]
+build-frontend = "build"
+environment.ANDROID_API_LEVEL = "24"
+
+[tool.ruff]
+indent-width = 2