Add prebuilt Packages

.github/workflows/CI.yml

@@ -0,0 +1,150 @@
+name: CI
+
+on:
+  push:
+    branches: [ "main" ]
+    tags:
+      - v*
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  check-python-style:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Set up Python 3.9
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.9
+
+      - name: Setup UV
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+
+      - name: Install dependencies
+        run: |
+          uv pip install --system black==24.* flake8==7.* flake8-pyproject==1.* isort==5.*
+
+      - name: Check code format with Black
+        run: |
+          black --check ctc_forced_aligner/*.py
+
+      - name: Check imports order with isort
+        run: |
+          isort --check-only ctc_forced_aligner/*.py
+
+      - name: Check code style with Flake8
+        run: |
+          flake8 ctc_forced_aligner/*.py
+
+  build-python-wheels:
+    needs: [check-python-style]
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-20.04, windows-2019, macos-14]
+        arch: [auto64]
+        include:
+        - os: ubuntu-20.04
+          arch: aarch64
+        - os: windows-2019
+          arch: ARM64
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - uses: docker/setup-qemu-action@v3
+        if: ${{ matrix.arch == 'aarch64' }}
+        name: Set up QEMU
+
+      - name: Setup UV
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+
+      - name: Build wheels
+        uses: pypa/[email protected]
+        with:
+          output-dir: python/wheelhouse
+        env:
+          CIBW_MANYLINUX_X86_64_IMAGE: manylinux2014
+          CIBW_MANYLINUX_AARCH64_IMAGE: manylinux2014
+          CIBW_ARCHS: ${{ matrix.arch }}
+          CIBW_SKIP: pp* *-musllinux_*
+          CIBW_BUILD_FRONTEND: "build[uv]"
+
+      - name: Upload Python wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-wheels-${{ runner.os }}-${{ matrix.arch }}
+          path: python/wheelhouse
+
+  test-python-wheels:
+    # We could test the Python wheels using cibuildwheel but we prefer to run the tests outside
+    # the build environment to ensure wheels correctly embed all dependencies.
+    needs: [build-python-wheels]
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        os: [ubuntu-20.04, windows-2019, macos-14]
+        arch: [auto64]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Download Python wheels
+        uses: actions/download-artifact@v4
+        with:
+          pattern: python-wheels-${{ runner.os }}-${{ matrix.arch }}
+          merge-multiple: true
+          path: wheels
+
+      - name: Setup UV
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+
+      - name: Install wheel
+        shell: bash
+        run: |
+          wheel_name=$(find wheels -type f -name "*$(echo ${{ matrix.python-version }} | tr -d '.')*")
+          uv pip install --system "pytest-xdist" "$wheel_name[dev]" --extra-index-url https://download.pytorch.org/whl/cpu
+
+      - name: Run tests
+        shell: bash
+        run: |
+          pytest -v -n auto tests/
+
+  publish-python-wheels-on-pypi:
+    needs: [test-python-wheels]
+    if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download Python wheels
+        uses: actions/download-artifact@v4
+        with:
+          pattern: python-wheels-*
+          merge-multiple: true
+          path: .
+
+      - name: Publish Python wheels to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_API_TOKEN }}
+          packages-dir: .

ctc_forced_aligner/__init__.py

@@ -16,3 +16,5 @@
     split_text,
     text_normalize,
 )
+
+__version__ = "0.3.0"

pyproject.toml

@@ -4,16 +4,20 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ctc-forced-aligner"
-version = "0.2"
 description = "Text to speech alignment using CTC forced alignment"
 license = { text = "CC-BY-NC 4.0" }
 authors = [
   {name = "Mahmoud Ashraf", email = "[email protected]"},]
-dynamic = ["dependencies"]
+dynamic = ["version", "dependencies"]
+requires-python = ">= 3.9"
 
 [tool.setuptools.dynamic]
+version = {attr = "ctc_forced_aligner.__version__"}
 dependencies = {file = ["requirements.txt"]}
 
+[project.optional-dependencies]
+dev = ["black==23.*", "flake8==7.*", "flake8-pyproject==1.*", "isort==5.*", "pytest==7.*"]
+
 [project.urls]
 repository = "https://github.com/MahmoudAshraf97/ctc-forced-aligner"
 
@@ -26,4 +30,12 @@ ctc-forced-aligner = "ctc_forced_aligner.align:cli"
     "uroman/bin/**/*.*",
     "uroman/data/**/*.*",
     "uroman/lib/**/*.*",
-]
+]
+
+[tool.flake8]
+max-line-length = 100
+ignore = ["E203", "W503"]
+
+[tool.isort]
+profile = "black"
+lines_between_types = 1

setup.py

@@ -1,11 +1,12 @@
 from pybind11.setup_helpers import Pybind11Extension, build_ext
 from setuptools import setup
+import sys
 
 ext_modules = [
     Pybind11Extension(
         "ctc_forced_aligner.ctc_forced_aligner",
         ["ctc_forced_aligner/forced_align_impl.cpp"],
-        extra_compile_args=["-O3"],
+        extra_compile_args=["/O2"] if sys.platform == "win32" else ["-O3"],
     )
 ]
 

tests/test_alignment.py

@@ -0,0 +1,27 @@
+import numpy as np
+import pytest
+import torch
+import torchaudio.functional as F
+
+from ctc_forced_aligner.alignment_utils import forced_align
+
+
+@pytest.mark.parametrize(
+    "logprobs_size, vocab_size, targets_size",
+    [
+        (l, t, int(l * ratio))
+        for l in range(100, 60101, 20000)
+        for t in range(30, 41, 10)
+        for ratio in [0.4, 0.6]
+    ],
+)
+def test_alignment(logprobs_size, vocab_size, targets_size):
+    blank = 0
+    targets = torch.randint(blank + 1, vocab_size, (1, targets_size))
+    logprobs = torch.randn((1, logprobs_size, vocab_size + 1))
+    logprobs = 6.5 * logprobs - 13 # same distribution as default model logits
+
+    ctc_alignment = forced_align(logprobs.numpy(), targets.numpy())
+    torch_alignment = F.forced_align(logprobs, targets)
+
+    assert np.allclose(ctc_alignment[0], torch_alignment[0].numpy())