pyannote.database 6.1.0__tar.gz → 6.2.0__tar.gz

pyannote_database-6.2.0/.github/workflows/build-wheels.yml

@@ -0,0 +1,35 @@
+name: Build Wheels
+
+on:
+  workflow_call:
+    inputs:
+      release-tag:
+        description: Release tag; empty on pull requests
+        required: false
+        type: string
+        default: ""
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+          # hatch-vcs needs Git history and tags to derive the package version.
+          fetch-depth: 0
+      - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+      - uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        with:
+          python-version-file: .python-version
+      - name: Build wheel and source distribution
+        run: uv build
+      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: python-package-distributions
+          path: dist/
+          if-no-files-found: error
+          retention-days: ${{ inputs.release-tag != '' && 90 || 3 }}

pyannote_database-6.2.0/.github/workflows/ci.yml

@@ -0,0 +1,87 @@
+name: CI
+
+on:
+  pull_request:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+# lint (PR only)
+# build ──┬──► test ──────────┬──► publish (release only)
+#         └──► version-guard ─┘
+# ci-complete collects all required results.
+
+jobs:
+  lint:
+    if: github.event_name == 'pull_request'
+    uses: ./.github/workflows/lint.yml
+
+  build:
+    uses: ./.github/workflows/build-wheels.yml
+    with:
+      release-tag: ${{ github.event.release.tag_name || '' }}
+
+  test:
+    needs: build
+    uses: ./.github/workflows/test.yml
+
+  version-guard:
+    name: versions
+    if: github.event_name == 'release'
+    needs: build
+    uses: ./.github/workflows/version-guard.yml
+    with:
+      release-tag: ${{ github.event.release.tag_name }}
+
+  # PyPI trusted publishing must run in a top-level workflow.
+  publish:
+    if: github.event_name == 'release'
+    needs: [build, test, version-guard]
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/project/pyannote-database/
+    permissions:
+      contents: write
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Upload distributions to GitHub Release
+        uses: softprops/action-gh-release@3d0d9888cb7fd7b750713d6e236d1fcb99157228 # v3.0.2
+        with:
+          tag_name: ${{ github.event.release.tag_name }}
+          files: |
+            dist/*.whl
+            dist/*.tar.gz
+          fail_on_unmatched_files: true
+      - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+      - name: Upload to PyPI
+        run: >-
+          uv publish --trusted-publishing always
+          --publish-url https://upload.pypi.org/legacy/
+          --check-url https://pypi.org/simple/
+
+  ci-complete:
+    if: always()
+    needs: [lint, build, test, version-guard, publish]
+    runs-on: ubuntu-latest
+    env:
+      RESULTS: ${{ join(needs.*.result, ' ') }}
+    steps:
+      - name: Check results
+        run: |
+          for result in $RESULTS; do
+            if [[ "$result" == failure || "$result" == cancelled ]]; then
+              echo "::error::Required job finished with result: $result"
+              exit 1
+            fi
+          done

pyannote_database-6.2.0/.github/workflows/doc.yml

@@ -0,0 +1,55 @@
+name: Documentation
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+          # hatch-vcs needs Git history and tags to derive the package version.
+          fetch-depth: 0
+      - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+      - uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        with:
+          python-version-file: .python-version
+      - name: Install documentation dependencies
+        run: |
+          uv venv
+          uv pip install '.[doc,cli]'
+      - name: Build documentation
+        run: uv run --no-project --python .venv/bin/python sphinx-build -W --keep-going -b html doc/source doc/build/html
+      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: documentation
+          path: doc/build/html
+          include-hidden-files: true
+          retention-days: 3
+
+  deploy:
+    if: github.event_name == 'push'
+    needs: build
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: documentation
+          path: doc/build/html
+      - uses: peaceiris/actions-gh-pages@373f7f263a76c20808c831209c920827a82a2847 # v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: doc/build/html

pyannote_database-6.2.0/.github/workflows/lint.yml

@@ -0,0 +1,30 @@
+name: Lint
+
+on:
+  workflow_call:
+
+permissions:
+  contents: read
+
+jobs:
+  ruff:
+    name: python
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      # Report lint/format issues without blocking PRs.
+      # Remove continue-on-error once the codebase is clean.
+      - name: Run ruff check
+        uses: astral-sh/ruff-action@0ce1b0bf8b818ef400413f810f8a11cdbda0034b # v4.0.0
+        continue-on-error: true
+        with:
+          version: "0.17.1"
+          args: "check ."
+      - name: Run ruff format
+        uses: astral-sh/ruff-action@0ce1b0bf8b818ef400413f810f8a11cdbda0034b # v4.0.0
+        continue-on-error: true
+        with:
+          version: "0.17.1"
+          args: "format --check ."

pyannote_database-6.2.0/.github/workflows/test.yml

@@ -0,0 +1,59 @@
+name: Test
+
+on:
+  workflow_call:
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    name: Test Python ${{ matrix.python-version }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12", "3.13", "3.14", "3.15", "3.x"]
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+      - id: python
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        with:
+          python-version: ${{ matrix.python-version }}
+          check-latest: ${{ matrix.python-version == '3.x' }}
+      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Install the built wheel with test dependencies
+        run: |
+          uv venv --python "${{ steps.python.outputs.python-path }}"
+          uv pip install "$(echo dist/*.whl)[test]"
+      - name: Run tests against the installed wheel
+        run: uv run --no-project --python .venv/bin/python python -m pytest tests
+
+  optional-features:
+    name: Optional features (Python 3.11)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+      - id: python
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        with:
+          python-version: "3.11"
+      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Install the built wheel with test dependencies
+        run: |
+          uv venv --python "${{ steps.python.outputs.python-path }}"
+          uv pip install "$(echo dist/*.whl)[test,cli,transcription]"
+      - name: Run tests against the installed wheel
+        run: uv run --no-project --python .venv/bin/python python -m pytest tests/test_optional_features.py

pyannote_database-6.2.0/.github/workflows/version-guard.yml

@@ -0,0 +1,70 @@
+name: Version Guard
+
+on:
+  workflow_call:
+    inputs:
+      release-tag:
+        description: Release tag expected to match the package version
+        required: true
+        type: string
+
+permissions:
+  contents: read
+
+jobs:
+  not-already-published:
+    name: pyannote-database
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        with:
+          python-version-file: .python-version
+      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Compare distributions with PyPI
+        env:
+          RELEASE_TAG: ${{ inputs.release-tag }}
+        shell: python
+        run: |
+          import hashlib
+          import json
+          import os
+          from pathlib import Path
+          from urllib.error import HTTPError
+          from urllib.request import urlopen
+          from zipfile import ZipFile
+          from email.parser import BytesParser
+
+
+          directory = Path("dist")
+          tag = os.environ["RELEASE_TAG"]
+          wheels = list(directory.glob("*.whl"))
+          sources = list(directory.glob("*.tar.gz"))
+          if len(wheels) != 1 or len(sources) != 1:
+              raise ValueError("Expected exactly one wheel and one source distribution")
+          with ZipFile(wheels[0]) as wheel:
+              metadata_path, = [n for n in wheel.namelist() if n.endswith(".dist-info/METADATA")]
+              metadata = BytesParser().parsebytes(wheel.read(metadata_path))
+          version = metadata["Version"]
+          if metadata["Name"] != "pyannote-database" or version != tag.removeprefix("v"):
+              raise ValueError(f"Release tag {tag!r} does not match pyannote-database {version}")
+          try:
+              with urlopen(f"https://pypi.org/pypi/pyannote-database/{version}/json", timeout=30) as response:
+                  published = json.load(response)["urls"]
+          except HTTPError as error:
+              if error.code != 404:
+                  raise
+              published = []
+          hashes = {item["filename"]: item["digests"]["sha256"] for item in published}
+          for artifact in wheels + sources:
+              if artifact.name not in hashes:
+                  print(f"{artifact.name}: not published yet")
+              elif hashlib.sha256(artifact.read_bytes()).hexdigest() == hashes[artifact.name]:
+                  print(f"{artifact.name}: already published with identical contents")
+              else:
+                  raise ValueError(f"{artifact.name} already exists with different contents. Use a new version.")

{pyannote_database-6.1.0 → pyannote_database-6.2.0}/.gitignore

@@ -89,3 +89,10 @@ ENV/
 .ropeproject
 
 .mypy_cache
+
+.venv/
+.ruff_cache/
+.pytest_cache/
+
+# Local dependency resolution
+uv.lock

pyannote_database-6.2.0/.pre-commit-config.yaml

@@ -0,0 +1,7 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.17.1
+    hooks:
+      - id: ruff-check
+        args: [--fix]
+      - id: ruff-format

pyannote_database-6.2.0/CHANGELOG.md

@@ -0,0 +1,297 @@
+# Changelog
+
+## Version 6.2.0 (2026-11-02)
+
+- BREAKING: require Python 3.11 or newer; Python 3.10 is no longer supported
+- BREAKING: forbid `@` in protocol names (now used to select a version)
+- BREAKING: reserve `version` key in subsets (now used to store the annotation version)
+- feat: add annotation versions with optional metadata (selected with `Database.Task.Protocol@version`)
+- feat: add `PYANNOTE_DATABASE_DATA_DIRS` environment variable to set root directories of relative `Databases:` paths
+- fix: resolve meta-protocol members using the registry that loaded them
+- fix: support `X` meta-protocols with Python 3.14
+- fix: `FileFinder` patterns only match files (not directories nor hidden files)
+
+## Version 6.1.1 (2025-12-07)
+
+- fix: fix warning about invalid espace sequence
+
+## Version 6.1.0 (2025-09-19)
+
+- BREAKING: update `STMLoader` to return `meeteval.io.SegLST` instances
+
+## Version 6.0.0 (2025-09-09)
+
+- BREAKING: drop support to `Python` < 3.10
+- BREAKING: switch to native namespace package 
+- setup: switch to `uv`
+
+## Version 5.1.3 (2025-01-15)
+
+- chore: remove deprecated use of `delim_whitespace`
+- chore: use `importlib.metadata` instead of `pkg_resources`
+
+## Version 5.1.0 (2024-04-05)
+
+- BREAKING: switch to python 3.9+ (no support for 3.12 yet)
+- feat(registry): make registry iterable (yields protocol names)
+- fix(setup): fix `typer`` dependency
+
+## Version 5.0.1 (2023-04-21)
+
+- fix: fix support for numeric values in custom protocols (e.g. `channel: 0`)
+- improve: do not complain about missing scope for meta protocols
+
+## Version 5.0.0 (2023-03-27)
+
+- feat(registry): add pyannote.database.registry to load multiple YAML configuration file
+- BREAKING: turn pyannote.database.get_{database|protocol|protocols} function into registry methods
+- BREAKING: remove support for database plugins (via "pyannote.database.database" entrypoint)
+- feat(protocol): add generic segmentation protocol with "classes" metadata
+- feat(protocol): add support for label "scope" in speaker diarization protocols
+- improve(protocol): make ProtocolFile pickable
+- feat(loader): add support for LAB and STM files
+- feat(loader): add option to filter RTTM lines by "type"
+- fix(cli): fix corner case when annotation key is missing
+
+## Version 4.1.3 (2022-02-11)
+
+- fix: fix corner case with missing uris in RTTM and UEM files
+- fix(CI): fix documentation deployment
+
+## Version 4.1.1 (2021-08-4)
+
+- fix: fix support for meta verification protocol
+
+## Version 4.1 (2021-04-07)
+
+- feat: make {RTTM|UEM}Loader usable as preprocessors
+- improve: remove the need for underscore prefix in database.yml
+- fix: fix ProtocolFile.__iter__ (dictionary changed size during iteration)
+
+## Version 4.0.4 (2020-12-14)
+
+- fix: fix ProtocolFile.__iter__ (dictionary changed size during iteration)
+
+## Version 4.0.3 (2020-10-11)
+
+- fix: make custom protocols pickable
+
+## Version 4.0.2 (2020-10-02)
+
+- feat: automagically crop "annotated" to file "duration" when available
+- fix: fix a bug in SpeakerDiarizationProtocols
+- improve: avoid loading ProtocolFile (lazy) keys in "get_unique_identifier"
+
+## Version 4.0.1 (2020-06-26)
+
+- feat: set "name" attribute in get_protocol
+- fix: display warning only when precomputed value is modified
+
+## Version 4.0 (2020-06-15)
+
+- feat: add support for custom speaker verification protocols
+- feat: add pyannote.database.loader entrypoint
+- feat: add pyannote-database CLI
+- feat: add a few dataloaders (RTTM, UEM, CTM, MAP)
+- feat: add support for nested ProtocolFile
+- doc: major documentation update (README and docstrings)
+- BREAKING: custom protocols must define a "uri" section
+- BREAKING: remove support for "preprocessors" in Database constructor
+- BREAKING: remove support for progress bars
+
+## Version 3.0.1 (2020-03-31)
+
+- BREAKING (feat): if a "database.yml" file exists in current working directory, it will be used even if PYANNOTE_DATABASE_CONFIG is set to another value.
+- feat: add support in FileFinder for paths relative to "database.yml"
+- BREAKING: rename "config_yml" option to "database_yml" in FileFinder
+- feat: add support in custom protocols for paths relative to "database.yml" (@PaulLerner)
+- BREAKING (feat): use "annotated" to crop "annotation" in custom protocols (@PaulLerner)
+- fix: add support for int-like protocol name in custom protocols (@PaulLerner)
+
+## Version 2.5 (2020-02-04)
+
+- BREAKING: refactor {current | protocol}_file_iter
+- BREAKING: only rely on "uri" to decide if a ProtocolFile contains multiple files
+- BREAKING: deprecate FileFinder.current_file_iter in favor of ProtocolFile.files
+- BREAKING: deprecate FileFinder.protocol_file_iter in favor of Protocol.files
+- fix: fix support for lazy preprocessors in {Protocol | ProtocolFile}.files
+
+## Version 2.4.3 (2020-01-24)
+
+- fix: fix infinite recursion in "ProtocolFile" lazy evaluation
+
+## Version 2.4.2 (2020-01-06)
+
+- fix: add support for int-like database name in custom protocol
+
+## Version 2.4.1 (2019-12-20)
+
+- fix: make ProtocolFile thread-safe
+
+## Version 2.4 (2019-12-17)
+
+- feat: make preprocessors lazy
+- fix: pandas would convert a label to NaN ([@PaulLerner](https://github.com/PaulLerner))
+- feat: setup continuous integration
+- setup: switch to pyannote.core 3.2
+
+## Version 2.3.1 (2019-09-04)
+
+- fix: fix support for MDTM files in `pyannote.database.custom.subset_iter` ([#23](https://github.com/pyannote/pyannote-database/issues/23))
+
+## Version 2.3 (2019-07-19)
+
+- feat: add LabelMapper preprocessor ([@MarvinLvn](https://github.com/MarvinLvn))
+- chore: replace (deprecated) pandas.read_table with pandas.read_csv ([@V-assim](https://github.com/V-assim))
+- chore: use YAML safe loader ([@V-assim](https://github.com/V-assim))
+
+## Version 2.2 (2019-06-26)
+
+- setup: switch to pyannote.core 3.0
+- feat: add RTTMLoader preprocessor
+
+## Version 2.1 (2019-04-04)
+
+- feat: add support for "domain" key in generic protocol
+
+## Version 2.0 (2019-03-20)
+
+- BREAKING: change location and format of pyannote.database configuration file
+- feat: add support for PYANNOTE_DATABASE_CONFIG environment variable
+
+## Version 1.6 (2019-03-12)
+
+- feat: add support for [file-based speaker diarization protocols](https://github.com/pyannote/pyannote-database/tree/develop#generic-speaker-diarization-protocols)
+- setup: switch to pyannote.core 2.1
+
+## Version 1.5.5 (2018-11-30)
+
+- fix: fix Collection.files when progress=True
+
+## Version 1.5.4 (2018-11-14)
+
+- fix: skip files with no "uri" entry in FileFinder.protocol_file_iter
+
+## Version 1.5.3 (2018-11-08)
+
+- fix: fix broken SpeakerVerificationProtocol
+
+## Version 1.5.1 (2018-10-16)
+
+- fix: fix support for string preprocessors
+
+## Version 1.5 (2018-09-25)
+
+- BREAKING: simplify SpeakerVerificationProtocol with {subset}_trial methods
+
+## Version 1.4 (2018-07-13)
+
+- feat: add raw collection protocol
+
+## Version 1.3.2 (2018-05-16)
+
+- fix: fix regression introduced in 1.3.1
+
+## Version 1.3.1 (2018-05-11)
+
+- fix: fix bug in `FileFinder.protocol_file_iter` with empty iterators
+
+## Version 1.3 (2018-02-04)
+
+- feat: add `extra_keys` parameter to `{protocol | current}_file_iter`
+
+## Version 1.2.1 (2018-02-03)
+
+- setup: drop support for Python 2
+- feat: add `protocol_file_iter` and `current_file_iter` to FileFinder
+- feat: add `get_label_identifier` utility function
+- fix: fix "get_unique_identifier" when "database" or "channel" is None
+
+## Version 1.1 (2017-10-13)
+
+- feat: add speaker identification protocol
+- feat: add speaker verification protocols
+- feat: add support for list of uris in FileFinder
+
+## Version 1.0 (2017-10-02)
+
+- feat: add support for "meta" protocols
+- feat: add speaker spotting protocol
+- setup: switch to pyannote.core 1.1
+
+## Version 0.12 (2017-06-28)
+
+- feat: add utility functions at package root
+- doc: improve documentation
+- doc: add link to pyannote-db-template repository
+
+## Version 0.11.2 (2017-03-15)
+
+- fix: fix a bug with string template preprocessors
+- doc: improve documentation
+
+## Version 0.11.1 (2017-01_16)
+
+- feat: add 'get_protocol' helper function
+
+## Version 0.11 (2017-01-11)
+
+- feat: add support for validation on training set to speaker recognition protocols
+- feat: add 'get_annotated' helper function
+
+## Version 0.10.2 (2017-01-04)
+
+- fix: fix bug in FileFinder
+
+## Version 0.10.1 (2016-12-17)
+
+- improve: change signature of preprocessor.__call__
+
+## Version 0.9 (2016-12-14)
+
+- feat: add "get_unique_identifier" utility function
+
+## Version 0.8.1 (2016-12-12)
+
+- fix: fix progress bar support
+
+## Version 0.8 (2016-12-06)
+
+- feat: add progress bar support
+
+## Version 0.7.1 (2016-12-03)
+
+- fix: add 'yield_name' parameter to speaker recognition generators
+
+## Version 0.7 (2016-12-02)
+
+- feat: add speaker recognition protocol
+
+## Version 0.6.1 (2016-12-02)
+
+- feat: add FileFinder utility class
+- fix: fix SpeakerDiarizationProtocol.stats()
+
+## Version 0.5 (2016-12-01)
+
+- BREAKING: replace 'medium_template' by (more generic) 'preprocessors'
+
+## Version 0.4.1 (2016-11-17)
+
+- fix: rename 'speakers' to 'labels' in statistics dictionary
+
+## Version 0.4 (2016-10-27)
+
+- feat: add a method providing global statistics about a subset
+
+## Version 0.3 (2016-09-22)
+
+- feat: add support for multiple media
+
+## Version 0.2 (2016-09-21)
+
+- feat: add support for 'medium_template' attribute
+
+## Version 0.1 (2016-09-20)
+
+- first public version