pstrain 0.1.0__tar.gz

pstrain-0.1.0/.github/dependabot.yml

@@ -0,0 +1,21 @@
+version: 2
+updates:
+  # Keep GitHub Actions up to date
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    groups:
+      actions:
+        patterns:
+          - "*"
+
+  # Keep Python dependencies up to date
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "monthly"
+    groups:
+      python-deps:
+        patterns:
+          - "*"

pstrain-0.1.0/.github/workflows/build.yml

@@ -0,0 +1,76 @@
+name: Build
+
+# Builds the sdist and platform wheels for packaging-relevant changes and on demand.
+# A weekly scheduled build detects packaging drift when those files do not change.
+
+on:
+  push:
+    branches: [master, main]
+    paths:
+      - csrc/**
+      - CMakeLists.txt
+      - pyproject.toml
+      - .github/workflows/build.yml
+  pull_request:
+    branches: [master, main]
+    paths:
+      - csrc/**
+      - CMakeLists.txt
+      - pyproject.toml
+      - .github/workflows/build.yml
+  workflow_dispatch:
+  schedule:
+    - cron: "17 4 * * 1"
+
+# Cancel superseded branch/PR runs; never auto-cancel default-branch runs so mainline gets a complete verdict.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' && github.ref != 'refs/heads/master' }}
+
+jobs:
+  # Build source distribution
+  build-sdist:
+    name: Build source distribution
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Build SDist
+        run: pipx run build --sdist
+
+      - uses: actions/upload-artifact@v7
+        with:
+          name: sdist
+          path: dist/*.tar.gz
+
+      - name: Test installed source distribution from a neutral directory
+        run: |
+          python -m venv "$RUNNER_TEMP/sdist-test"
+          "$RUNNER_TEMP/sdist-test/bin/pip" install dist/*.tar.gz
+          cd "$RUNNER_TEMP"
+          "$RUNNER_TEMP/sdist-test/bin/python" "$GITHUB_WORKSPACE/scripts/test_installed_distribution.py"
+
+  # Build wheels on multiple platforms.
+  # Windows is intentionally omitted: the vendored CMU Sphinx C does not yet
+  # build under MSVC (POSIX-only drand48 and several unresolved sphinx3_align
+  # symbols). Restore windows-latest here once that portability work is done.
+  build-wheels:
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v4.2
+
+      - name: Verify emitted floating-point contraction policy in wheels
+        run: python scripts/check_fp_contract.py --wheels wheelhouse
+
+      - uses: actions/upload-artifact@v7
+        with:
+          name: wheels-${{ matrix.os }}
+          path: ./wheelhouse/*.whl

pstrain-0.1.0/.github/workflows/docs.yml

@@ -0,0 +1,34 @@
+name: Docs
+
+on:
+  push:
+    branches: [master, main]
+    paths:
+      - "docs/**"
+      - "pstrain/lib/config/**"
+      - "pyproject.toml"
+      - ".github/workflows/docs.yml"
+  pull_request:
+    branches: [master, main]
+    paths:
+      - "docs/**"
+      - "pstrain/lib/config/**"
+      - "pyproject.toml"
+      - ".github/workflows/docs.yml"
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' && github.ref != 'refs/heads/master' }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+      - uses: actions/setup-python@v7
+        with:
+          python-version: "3.12"
+      - run: pip install -e ".[docs]"
+      - name: Build documentation
+        run: sphinx-build -b html docs docs/_build/html

pstrain-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,72 @@
+name: Release
+
+# Build wheels + sdist and publish pstrain to PyPI via Trusted Publishing (OIDC).
+# Triggered when a GitHub Release is published; also runnable on demand to rehearse
+# the build (the publish step only runs for release events).
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+concurrency:
+  group: release-${{ github.ref }}
+  cancel-in-progress: false
+
+jobs:
+  build-wheels:
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+    steps:
+      - uses: actions/checkout@v7
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v4.2
+      - name: Verify emitted floating-point contraction policy in wheels
+        run: python scripts/check_fp_contract.py --wheels wheelhouse
+      - uses: actions/upload-artifact@v7
+        with:
+          name: dist-wheels-${{ matrix.os }}
+          path: ./wheelhouse/*.whl
+
+  build-sdist:
+    name: Build source distribution
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+      - name: Build SDist
+        run: pipx run build --sdist
+      - name: Test installed source distribution from a neutral directory
+        run: |
+          python -m venv "$RUNNER_TEMP/sdist-test"
+          "$RUNNER_TEMP/sdist-test/bin/pip" install dist/*.tar.gz
+          cd "$RUNNER_TEMP"
+          "$RUNNER_TEMP/sdist-test/bin/python" "$GITHUB_WORKSPACE/scripts/test_installed_distribution.py"
+      - uses: actions/upload-artifact@v7
+        with:
+          name: dist-sdist
+          path: dist/*.tar.gz
+
+  publish:
+    name: Publish to PyPI
+    needs: [build-wheels, build-sdist]
+    runs-on: ubuntu-latest
+    # Only publish for a real published Release, never for workflow_dispatch rehearsals.
+    if: github.event_name == 'release'
+    environment:
+      name: pypi
+      url: https://pypi.org/p/pstrain
+    permissions:
+      id-token: write   # OIDC token for Trusted Publishing; no API token needed.
+    steps:
+      - name: Download all distribution artifacts
+        uses: actions/download-artifact@v7
+        with:
+          path: dist
+          pattern: dist-*
+          merge-multiple: true
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

pstrain-0.1.0/.github/workflows/tests.yml

@@ -0,0 +1,204 @@
+# Always report required test contexts; expensive steps no-op for docs-only changes.
+name: Tests
+
+on:
+  push:
+    branches: [master, main]
+  pull_request:
+    branches: [master, main]
+  workflow_dispatch:
+
+# Cancel superseded branch/PR runs; never auto-cancel default-branch runs so mainline gets a complete verdict.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' && github.ref != 'refs/heads/master' }}
+
+jobs:
+  changes:
+    name: Detect code changes
+    runs-on: ubuntu-latest
+    outputs:
+      code: ${{ steps.filter.outputs.code }}
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Classify changed paths
+        id: filter
+        uses: dorny/paths-filter@v3
+        with:
+          filters: |
+            code:
+              - '!**.md'
+              - '!docs/**'
+
+  # C library tests
+  c-tests:
+    name: C tests on ${{ matrix.os }}
+    needs: changes
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Configure
+        if: needs.changes.outputs.code == 'true'
+        run: cmake -S . -B build -DCMAKE_BUILD_TYPE=Debug -DBUILD_CLI=ON
+
+      - name: Build
+        if: needs.changes.outputs.code == 'true'
+        run: cmake --build build
+
+      - name: Test
+        if: needs.changes.outputs.code == 'true'
+        # --no-tests=error guards against silently passing on an empty test
+        # set (the previous failure mode: no add_test() anywhere).
+        run: ctest --test-dir build --output-on-failure --no-tests=error
+
+      - name: Verify emitted floating-point contraction policy
+        if: needs.changes.outputs.code == 'true'
+        run: python scripts/check_fp_contract.py build
+
+  # Linux-only sanitizer coverage. AppleClang is excluded because ASan hangs
+  # before main on macOS in this project.
+  c-tests-sanitizers:
+    name: C tests with ASan and UBSan on Linux
+    needs: changes
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Configure
+        if: needs.changes.outputs.code == 'true'
+        run: >-
+          cmake -S . -B build
+          -DCMAKE_BUILD_TYPE=Debug
+          -DBUILD_CLI=ON
+          -DCMAKE_C_FLAGS="-fsanitize=address,undefined -fno-omit-frame-pointer"
+
+      - name: Build
+        if: needs.changes.outputs.code == 'true'
+        run: cmake --build build
+
+      - name: Test
+        if: needs.changes.outputs.code == 'true'
+        env:
+          ASAN_OPTIONS: halt_on_error=1
+          UBSAN_OPTIONS: halt_on_error=1:print_stacktrace=1
+        run: ctest --test-dir build --output-on-failure --no-tests=error
+
+  # Python tests across versions
+  python-tests:
+    name: Python ${{ matrix.python }} on ${{ matrix.os }}
+    needs: changes
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        # PRs test boundary Python versions on Ubuntu plus one representative
+        # framework-Python leg on macOS; other events run the full matrix.
+        include: ${{ github.event_name == 'pull_request' && fromJSON('[{"python":"3.11","os":"ubuntu-latest"},{"python":"3.13","os":"ubuntu-latest"},{"python":"3.13","os":"macos-latest"}]') || fromJSON('[{"python":"3.11","os":"ubuntu-latest"},{"python":"3.11","os":"macos-latest"},{"python":"3.12","os":"ubuntu-latest"},{"python":"3.12","os":"macos-latest"},{"python":"3.13","os":"ubuntu-latest"},{"python":"3.13","os":"macos-latest"}]') }}
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Set up Python ${{ matrix.python }}
+        if: needs.changes.outputs.code == 'true'
+        uses: actions/setup-python@v7
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install dependencies
+        if: needs.changes.outputs.code == 'true'
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest pytest-cov
+
+      - name: Build C library
+        if: needs.changes.outputs.code == 'true'
+        run: |
+          cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DBUILD_CLI=ON
+          cmake --build build
+
+      - name: Verify emitted floating-point contraction policy
+        if: needs.changes.outputs.code == 'true'
+        run: python scripts/check_fp_contract.py build
+
+      - name: Install package (editable)
+        if: needs.changes.outputs.code == 'true'
+        run: pip install -e ".[dev,test]"
+
+      - name: Run tests
+        if: needs.changes.outputs.code == 'true'
+        # PSTRAIN_REQUIRE_CLIB=1 turns "C library not loadable" from a silent
+        # skip into a hard failure, so this job can't go green while the
+        # entire CFFI/parity tier is quietly skipped.
+        env:
+          PSTRAIN_REQUIRE_CLIB: "1"
+        run: pytest -v --cov=pstrain --cov-report=xml
+
+      - name: Verify canonical config consumers and generated reference
+        if: needs.changes.outputs.code == 'true' && matrix.python == '3.11' && matrix.os == 'ubuntu-latest'
+        # This is an installed-package job; the ambient gate is exercised by
+        # the in-tree verified flow and must reject this editable installation.
+        run: make AMBIENT_IMPORT_PREREQUISITE= config-check
+
+      - name: Upload coverage
+        uses: codecov/codecov-action@v7
+        if: needs.changes.outputs.code == 'true' && matrix.python == '3.12' && matrix.os == 'ubuntu-latest'
+        with:
+          files: ./coverage.xml
+          fail_ci_if_error: false
+
+  # Lint checks
+  lint:
+    name: Lint
+    needs: changes
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Set up Python
+        if: needs.changes.outputs.code == 'true'
+        uses: actions/setup-python@v7
+        with:
+          python-version: "3.12"
+
+      - name: Install dependencies
+        if: needs.changes.outputs.code == 'true'
+        run: |
+          python -m pip install --upgrade pip
+          pip install ruff mypy
+
+      - name: Run ruff
+        if: needs.changes.outputs.code == 'true'
+        run: ruff check pstrain/ tests/
+
+      - name: Run ruff format check
+        if: needs.changes.outputs.code == 'true'
+        run: ruff format --check pstrain/ tests/
+
+  # Type checking (strict mypy, blocking).
+  typecheck:
+    name: Type check
+    needs: changes
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Set up Python
+        if: needs.changes.outputs.code == 'true'
+        uses: actions/setup-python@v7
+        with:
+          python-version: "3.12"
+
+      - name: Install dependencies
+        if: needs.changes.outputs.code == 'true'
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+
+      - name: Run mypy
+        if: needs.changes.outputs.code == 'true'
+        run: mypy pstrain/ --ignore-missing-imports

pstrain-0.1.0/.github/workflows/windows-scoping.yml

@@ -0,0 +1,107 @@
+name: Windows native build
+
+on:
+  push:
+    branches: [master, main]
+  pull_request:
+    branches: [master, main]
+
+# Cancel superseded PR runs; never auto-cancel default-branch runs so mainline gets a complete verdict.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' && github.ref != 'refs/heads/master' }}
+
+jobs:
+  windows-native-build:
+    name: Windows native build (${{ matrix.compiler }})
+    runs-on: windows-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        compiler: [msvc, clang-cl]
+
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Enter the MSVC developer environment
+        uses: ilammy/msvc-dev-cmd@v1
+
+      - name: Configure (${{ matrix.compiler }})
+        shell: pwsh
+        run: |
+          $build = "build-${{ matrix.compiler }}"
+          $compilerArgs = @()
+          if ("${{ matrix.compiler }}" -eq "clang-cl") {
+            $compilerArgs += "-T"
+            $compilerArgs += "ClangCL"
+          }
+          cmake -S . -B $build `
+            -DBUILD_SHARED_LIBS=ON `
+            -DBUILD_CLI=ON `
+            @compilerArgs
+
+      - name: Build static core, shared core, and CLI programs (${{ matrix.compiler }})
+        shell: pwsh
+        run: cmake --build "build-${{ matrix.compiler }}" --config Release --parallel
+
+  windows-python-tests:
+    name: Windows Python 3.13 tests
+    runs-on: windows-latest
+
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Set up Python 3.13
+        uses: actions/setup-python@v7
+        with:
+          python-version: "3.13"
+
+      - name: Enter the MSVC developer environment
+        uses: ilammy/msvc-dev-cmd@v1
+
+      - name: Build native library and CLI programs
+        shell: pwsh
+        run: |
+          cmake -S . -B build -DBUILD_SHARED_LIBS=ON -DBUILD_CLI=ON
+          cmake --build build --config Release --parallel
+
+      - name: Install package and test dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev]"
+
+      - name: Run Windows-compatible Python tests
+        env:
+          PSTRAIN_REQUIRE_CLIB: "1"
+        shell: pwsh
+        run: |
+          python -m pytest -v -rs `
+            tests/test_paths.py `
+            tests/test_commands.py::TestCommandBuilder::test_resolution_uses_exe_suffix_on_windows `
+            tests/test_cffi_abi.py `
+            tests/test_lib_structure.py `
+            tests/test_pstrainc.py::test_library_loads `
+            tests/test_pstrainc.py::test_logmath_init_free `
+            tests/test_pstrainc.py::test_logmath_log_exp `
+            tests/test_pstrainc.py::test_logmath_add `
+            tests/test_pstrainc.py::test_logmath_get_base `
+            tests/test_pstrainc.py::test_logmath_edge_cases `
+            tests/test_pstrainc.py::test_logmath_different_bases `
+            tests/test_pstrainc.py::test_enum_constants `
+            tests/test_pstrainc.py::test_error_macros_exist `
+            tests/test_pstrainc.py::test_logmath_identity `
+            tests/test_pstrainc.py::test_logmath_add_commutative `
+            tests/test_pstrainc.py::test_pstrain_fe_create_default `
+            tests/test_pstrainc.py::test_pstrain_fe_create_custom `
+            tests/test_pstrainc.py::test_pstrain_fe_create_8khz `
+            tests/test_features.py::TestFEParams `
+            tests/test_features.py::TestReadWriteSphinxMfc `
+            tests/test_features.py::TestReadWav `
+            tests/test_bw_sharding.py `
+            tests/test_dtree.py `
+            tests/test_e2e_training.py `
+            tests/test_feat_params.py `
+            tests/test_numeric_harness.py `
+            tests/test_pipeline_tasks.py `
+            tests/test_train_convergence.py `
+            tests/test_train_retry.py

pstrain-0.1.0/.gitignore

@@ -0,0 +1,89 @@
+# local untracked cache
+untracked/
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+.Python
+build*/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+# Build artifacts (root level only, not pstrain/lib/)
+/lib/
+/lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+venv/
+.venv/
+ENV/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.nox/
+
+# mypy
+.mypy_cache/
+
+# ruff
+.ruff_cache/
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Documentation
+docs/_build/
+
+# Built C library artifacts
+pstrain/lib/_cffi/*.dylib
+pstrain/lib/_cffi/*.so
+pstrain/lib/_cffi/*.dll
+build.log
+
+# Testing data (do not commit)
+# CMU Arctic downloads and extracted data
+cmu_arctic/
+cmu_us_*_arctic/
+*.tar.bz2
+/Volumes/hacks/lenzo/pstrain/projects/
+.snakemake/
+
+# Generated training data and models
+audio/
+shared/
+experiments/
+dist/
+*.mfc
+*.wav
+/data/
+benchmarks/timit/data/
+benchmarks/timit/pilot/
+
+# ...but committed test fixtures are not generated artifacts. Keep them.
+# (These broad patterns over-reach — see plan 3.5; this negation is the
+# minimal fix so the mini_arctic e2e corpus is tracked.)
+!tests/fixtures/**
+!tests/fixtures/mini_arctic/wav/*.wav
+!pstrain/data/sample/*.wav
+.claude

pstrain-0.1.0/.pre-commit-config.yaml

@@ -0,0 +1,63 @@
+# Pre-commit hooks for pstrain
+# Install: pip install pre-commit && pre-commit install
+
+default_language_version:
+  python: python3.12
+
+repos:
+  # Basic file checks
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: trailing-whitespace
+        exclude: ^(build/|\.eggs/)
+      - id: end-of-file-fixer
+        exclude: ^(build/|\.eggs/)
+      - id: check-yaml
+      - id: check-toml
+      - id: check-json
+      - id: check-added-large-files
+        args: ['--maxkb=1000']
+        exclude: \.(wav|mp3|flac|ogg)$
+      - id: check-merge-conflict
+      - id: check-case-conflict
+      - id: mixed-line-ending
+        args: ['--fix=lf']
+
+  # Python code quality - Ruff (fast linter and formatter)
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.20
+    hooks:
+      # Run the linter
+      - id: ruff
+        args: [--fix]
+        files: ^(pstrain|tests)/
+        exclude: ^(build/|csrc/libs/libsphinxbase/(fe|util)/.*\.py$)
+      # Run the formatter
+      - id: ruff-format
+        files: ^(pstrain|tests)/
+        exclude: ^(build/|csrc/libs/libsphinxbase/(fe|util)/.*\.py$)
+
+  # Type checking with mypy
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v2.1.0
+    hooks:
+      - id: mypy
+        additional_dependencies: [pydantic==2.12.5, types-PyYAML==6.0.12.20250915, pytest==9.0.2]
+        exclude: ^(build/|\.eggs/|csrc/)
+        args: [pstrain, --ignore-missing-imports]
+        pass_filenames: false
+
+# Exclude certain paths globally
+exclude: |
+  (?x)^(
+      csrc/|
+      build/|
+      venv/|
+      \.eggs/|
+      \.git/|
+      \.mypy_cache/|
+      \.ruff_cache/|
+      __pycache__/|
+      \.pytest_cache/
+  )

pstrain-0.1.0/CHANGELOG.md

@@ -0,0 +1,14 @@
+# Changelog
+
+Release-relevant changes are recorded here. The project is currently an alpha;
+the version in `pyproject.toml` is authoritative.
+
+## 0.1.0 - Unreleased
+
+- Imported the original pstrain/SphinxTrain-derived codebase (2026-07-03).
+- Adopted the BSD 2-Clause license for new pstrain code while preserving the
+  notices and license terms of the CMU-derived C sources (2026-07-08).
+- Added and pinned the reproducible CMU Arctic benchmark baseline and its
+  immutable corpus metadata (2026-08-11).
+- Contained fatal native CFFI operations behind a reusable worker boundary and
+  completed the audited CFFI operation surface (2026-08-10 through 2026-08-11).