Merge branch 'release/3.2.0'

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,56 @@
+name: Bug report
+description: Report a bug in pyannote.audio
+body:
+
+- type: markdown
+  attributes:
+    value: |
+      When reporting bugs, please follow the guidelines in this template. This helps identify the problem precisely and thus enables contributors to fix it faster.
+      - Write a descriptive issue title above.
+      - The golden rule is to **always open *one* issue for *one* bug**. If you notice several bugs and want to report them, make sure to create one new issue for each of them.
+      - Search [open](https://github.com/pyannote/pyannote-audio/issues) and [closed](https://github.com/pyannote/pyannote-audio/issues?q=is%3Aissue+is%3Aclosed) issues to ensure it has not already been reported. If you don't find a relevant match or if you're unsure, don't hesitate to **open a new issue**. The bugsquad will handle it from there if it's a duplicate.
+      - Please always check if your issue is reproducible in the latest version – it may already have been fixed!
+      - If you use a custom build, please test if your issue is reproducible in official releases too.
+
+- type: textarea
+  attributes:
+    label: Tested versions
+    description: |
+      To properly fix a bug, we need to identify if the bug was recently introduced in the engine, or if it was always present.
+      - Please specify the pyannote.audio version you found the issue in, including the **Git commit hash** if using a development build.
+      - If you can, **please test earlier pyannote.audio versions** and, if applicable, newer versions (development branch). Mention whether the bug is reproducible or not in the versions you tested.
+      - The aim is for us to identify whether a bug is a **regression**, i.e. an issue that didn't exist in a previous version, but was introduced later on, breaking existing functionality. For example, if a bug is reproducible in 3.2 but not in 3.0, we would like you to test intermediate 3.1 to find which version is the first one where the issue can be reproduced.
+    placeholder: |
+      - Reproducible in: 3.1, 3.2, and later
+      - Not reproducible in: 3.0
+  validations:
+    required: true
+
+- type: input
+  attributes:
+    label: System information
+    description: |
+      - Specify the OS version, and when relevant hardware information.
+      - For issues that are likely OS-specific and/or GPU-related, please specify the GPU model and architecture.
+      - **Bug reports not including the required information may be closed at the maintainers' discretion.** If in doubt, always include all the requested information; it's better to include too much information than not enough information.
+    placeholder: macOS 13.6 - pyannote.audio 3.1.1 - M1 Pro
+  validations:
+    required: true
+
+- type: textarea
+  attributes:
+    label: Issue description
+    description: |
+      Describe your issue briefly. What doesn't work, and how do you expect it to work instead?
+      You can include audio, images or videos with drag and drop, and format code blocks or logs with <code>```</code> tags.
+  validations:
+    required: true
+
+- type: input
+  attributes:
+    label: Minimal reproduction example (MRE)
+    description: |
+      Having reproducible issues is a prerequisite for contributors to be able to solve them.
+      Include a link to minimal reproduction example using [this Google Colab notebook](https://colab.research.google.com/github/pyannote/pyannote-audio/blob/develop/tutorials/MRE_template.ipynb) as a starting point.
+  validations:
+    required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,15 @@
+blank_issues_enabled: false
+
+contact_links:
+
+  - name: Feature request
+    url: https://github.com/pyannote/pyannote-audio/discussions
+    about: Suggest an idea for this project.
+
+  - name: Consulting
+    url: https://herve.niderb.fr/consulting
+    about: Using pyannote.audio in production? Make the most of it thanks to our consulting services.
+
+  - name: Premium models
+    url: https://forms.office.com/e/GdqwVgkZ5C
+    about: We are considering selling premium models, extensions, or services around pyannote.audio.

.github/workflows/test.yml

@@ -30,4 +30,4 @@ jobs:
           pip install -e .[dev,testing]
       - name: Test with pytest
         run: |
-          pytest
+          pytest -k "not test_cli.py"

.github/workflows/test_cli.yml

@@ -0,0 +1,33 @@
+name: CLI tests
+
+on:
+  push:
+    branches: [develop]
+  pull_request:
+    branches: [develop]
+
+jobs:
+  build:
+    timeout-minutes: 20
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+        python-version: ["3.10"]
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install libsndfile
+        if: matrix.os == 'ubuntu-latest'
+        run: |
+          sudo apt-get update
+          sudo apt-get install libsndfile1
+      - name: Install pyannote.audio
+        run: |
+          pip install -e .[dev,testing,cli]
+      - name: Test with pytest
+        run: |
+          pytest tests/test_cli.py

.pre-commit-config.yaml

@@ -14,7 +14,7 @@ repos:
 
     # Sort imports
     - repo: https://github.com/PyCQA/isort
-      rev: 5.10.1
+      rev: 5.12.0
       hooks:
       - id: isort
         args: ["--profile", "black"]

CHANGELOG.md

@@ -1,5 +1,40 @@
 # Changelog
 
+## Version 3.2.0 (2024-05-08)
+
+### New features
+
+- feat(task): add option to cache task training metadata to speed up training (with [@clement-pages](https://github.com/clement-pages/))
+- feat(model): add `receptive_field`, `num_frames` and `dimension` to models (with [@Bilal-Rahou](https://github.com/Bilal-Rahou))
+- feat(model): add `fbank_only` property to `WeSpeaker` models
+- feat(util): add `Powerset.permutation_mapping` to help with permutation in powerset space (with [@FrenchKrab](https://github.com/FrenchKrab))
+- feat(sample): add sample file at `pyannote.audio.sample.SAMPLE_FILE`
+- feat(metric): add `reduce` option to `diarization_error_rate` metric (with [@Bilal-Rahou](https://github.com/Bilal-Rahou))
+- feat(pipeline): add `Waveform` and `SampleRate` preprocessors
+
+### Fixes
+
+- fix(task): fix random generators and their reproducibility (with [@FrenchKrab](https://github.com/FrenchKrab))
+- fix(task): fix estimation of training set size (with [@FrenchKrab](https://github.com/FrenchKrab))
+- fix(hook): fix `torch.Tensor` support in `ArtifactHook`
+- fix(doc): fix typo in `Powerset` docstring (with [@lukasstorck](https://github.com/lukasstorck))
+
+### Improvements
+
+- improve(metric): add support for number of speakers mismatch in `diarization_error_rate` metric
+- improve(pipeline): track both `Model` and `nn.Module` attributes in `Pipeline.to(device)`
+- improve(io): switch to `torchaudio >= 2.2.0`
+- improve(doc): update tutorials (with [@clement-pages](https://github.com/clement-pages/))
+
+## Breaking changes
+
+- BREAKING(model): get rid of `Model.example_output` in favor of `num_frames` method, `receptive_field` property, and `dimension` property
+- BREAKING(task): custom tasks need to be updated (see "Add your own task" tutorial)
+
+## Community contributions
+
+- community: add tutorial for offline use of `pyannote/speaker-diarization-3.1` (by [@simonottenhauskenbun](https://github.com/simonottenhauskenbun))
+
 ## Version 3.1.1 (2023-12-01)
 
 ### TL;DR

MANIFEST.in

@@ -1,4 +1,6 @@
 recursive-include pyannote *.py
 recursive-include pyannote *.yaml
+recursive-include pyannote *.wav
+recursive-include pyannote *.rttm
 global-exclude *.pyc
 global-exclude __pycache__

README.md

@@ -70,26 +70,30 @@ for turn, _, speaker in diarization.itertracks(yield_label=True):
 - Videos
   - [Introduction to speaker diarization](https://umotion.univ-lemans.fr/video/9513-speech-segmentation-and-speaker-diarization/) / JSALT 2023 summer school / 90 min
   - [Speaker segmentation model](https://www.youtube.com/watch?v=wDH2rvkjymY) / Interspeech 2021 / 3 min
-  - [First releaase of pyannote.audio](https://www.youtube.com/watch?v=37R_R82lfwA) / ICASSP 2020 / 8 min
+  - [First release of pyannote.audio](https://www.youtube.com/watch?v=37R_R82lfwA) / ICASSP 2020 / 8 min
+- Community contributions (not maintained by the core team)
+  - 2024-04-05 > [Offline speaker diarization (speaker-diarization-3.1)](tutorials/community/offline_usage_speaker_diarization.ipynb) by [Simon Ottenhaus](https://github.com/simonottenhauskenbun)
 
 ## Benchmark
 
 Out of the box, `pyannote.audio` speaker diarization [pipeline](https://hf.co/pyannote/speaker-diarization-3.1) v3.1 is expected to be much better (and faster) than v2.x.
 Those numbers are diarization error rates (in %):
 
-| Benchmark              | [v2.1](https://hf.co/pyannote/speaker-diarization-2.1) | [v3.1](https://hf.co/pyannote/speaker-diarization-3.1) | [Premium](https://forms.office.com/e/GdqwVgkZ5C) |
-| ---------------------- | ------------------------------------------------------ | ------------------------------------------------------ | ---------------------------------------------- |
-| AISHELL-4              | 14.1                                                   | 12.3                                                   | 11.9                                           |
-| AliMeeting (channel 1) | 27.4                                                   | 24.5                                                   | 22.5                                           |
-| AMI (IHM)              | 18.9                                                   | 18.8                                                   | 16.6                                           |
-| AMI (SDM)              | 27.1                                                   | 22.6                                                   | 20.9                                           |
-| AVA-AVD                | 66.3                                                   | 50.0                                                   | 39.8                                           |
-| CALLHOME (part 2)      | 31.6                                                   | 28.4                                                   | 22.2                                           |
-| DIHARD 3 (full)        | 26.9                                                   | 21.4                                                   | 17.2                                           |
-| Ego4D (dev.)           | 61.5                                                   | 51.2                                                   | 43.8                                           |
-| MSDWild                | 32.8                                                   | 25.4                                                   | 19.8                                           |
-| REPERE (phase2)        | 8.2                                                    | 7.8                                                    | 7.6                                            |
-| VoxConverse (v0.3)     | 11.2                                                   | 11.2                                                   | 9.4                                            |
+| Benchmark                                                                                                                   | [v2.1](https://hf.co/pyannote/speaker-diarization-2.1) | [v3.1](https://hf.co/pyannote/speaker-diarization-3.1) | [Premium](https://forms.office.com/e/GdqwVgkZ5C) |
+| --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ | ------------------------------------------------------ | ------------------------------------------------ |
+| [AISHELL-4](https://arxiv.org/abs/2104.03603)                                                                               | 14.1                                                   | 12.2                                                   | 11.9                                             |
+| [AliMeeting](https://www.openslr.org/119/) (channel 1)                                                                      | 27.4                                                   | 24.4                                                   | 22.5                                             |
+| [AMI](https://groups.inf.ed.ac.uk/ami/corpus/) (IHM)                                                                        | 18.9                                                   | 18.8                                                   | 16.6                                             |
+| [AMI](https://groups.inf.ed.ac.uk/ami/corpus/) (SDM)                                                                        | 27.1                                                   | 22.4                                                   | 20.9                                             |
+| [AVA-AVD](https://arxiv.org/abs/2111.14448)                                                                                 | 66.3                                                   | 50.0                                                   | 39.8                                             |
+| [CALLHOME](https://catalog.ldc.upenn.edu/LDC2001S97) ([part 2](https://github.com/BUTSpeechFIT/CALLHOME_sublists/issues/1)) | 31.6                                                   | 28.4                                                   | 22.2                                             |
+| [DIHARD 3](https://catalog.ldc.upenn.edu/LDC2022S14) ([full](https://arxiv.org/abs/2012.01477))                             | 26.9                                                   | 21.7                                                   | 17.2                                             |
+| [Earnings21](https://github.com/revdotcom/speech-datasets)                                                                  | 17.0                                                   | 9.4                                                    | 9.0                                              |
+| [Ego4D](https://arxiv.org/abs/2110.07058) (dev.)                                                                            | 61.5                                                   | 51.2                                                   | 43.8                                             |
+| [MSDWild](https://github.com/X-LANCE/MSDWILD)                                                                               | 32.8                                                   | 25.3                                                   | 19.8                                             |
+| [RAMC](https://www.openslr.org/123/)                                                                                        | 22.5                                                   | 22.2                                                   | 18.4                                             |
+| [REPERE](https://www.islrn.org/resources/360-758-359-485-0/) (phase2)                                                       | 8.2                                                    | 7.8                                                    | 7.6                                              |
+| [VoxConverse](https://github.com/joonson/voxconverse) (v0.3)                                                                | 11.2                                                   | 11.3                                                   | 9.4                                              |
 
 [Diarization error rate](http://pyannote.github.io/pyannote-metrics/reference.html#diarization) (in %)
 

pyannote/audio/augmentation/mix.py

@@ -60,10 +60,10 @@ def __init__(
         max_snr_in_db: float = 5.0,
         mode: str = "per_example",
         p: float = 0.5,
-        p_mode: str = None,
-        sample_rate: int = None,
-        target_rate: int = None,
-        max_num_speakers: int = None,
+        p_mode: Optional[str] = None,
+        sample_rate: Optional[int] = None,
+        target_rate: Optional[int] = None,
+        max_num_speakers: Optional[int] = None,
         output_type: str = "tensor",
     ):
         super().__init__(
@@ -80,7 +80,7 @@ def __init__(
 
     def randomize_parameters(
         self,
-        samples: Tensor = None,
+        samples: Optional[Tensor] = None,
         sample_rate: Optional[int] = None,
         targets: Optional[Tensor] = None,
         target_rate: Optional[int] = None,

pyannote/audio/cli/evaluate.py

@@ -25,7 +25,7 @@
 
 import hydra
 from omegaconf import DictConfig
-from pyannote.database import FileFinder, ProtocolFile, get_protocol
+from pyannote.database import FileFinder, ProtocolFile, registry
 from rich.progress import Progress
 
 from pyannote.audio import Inference, Model
@@ -41,8 +41,16 @@ def evaluate(cfg: DictConfig) -> Optional[float]:
     (device,) = get_devices(needs=1)
     model = Model.from_pretrained(cfg.model, device=device)
 
+    # load databases into registry if it was specified
+    if "registry" in cfg:
+        for database_yml in cfg.registry.split(","):
+            registry.load_database(database_yml)
+
     # load evaluation files
-    protocol = get_protocol(cfg.protocol, preprocessors={"audio": FileFinder()})
+    protocol = registry.get_protocol(
+        cfg.protocol, preprocessors={"audio": FileFinder()}
+    )
+
     files = list(getattr(protocol, cfg.subset)())
 
     # load evaluation metric
@@ -53,7 +61,7 @@ def evaluate(cfg: DictConfig) -> Optional[float]:
         main_task = progress.add_task(protocol.name, total=len(files))
         file_task = progress.add_task("Processing", total=1.0)
 
-        def progress_hook(completed: int = None, total: int = None):
+        def progress_hook(completed: Optional[int] = None, total: Optional[int] = None):
             progress.update(file_task, completed=completed / total)
 
         inference = Inference(model, device=device)
@@ -65,8 +73,6 @@ def hypothesis(file: ProtocolFile):
                 warm_up=(warm_up, warm_up),
             )
 
-        metric = DiscreteDiarizationErrorRate()
-
         for file in files:
             progress.update(file_task, description=file["uri"])
             reference = file["annotation"]

pyannote/audio/cli/evaluate_config/hydra/default.yaml

@@ -22,7 +22,8 @@ help:
   template: |-
     ${hydra.help.header}
 
-    pyannote-audio-eval protocol={protocol_name} 
+    pyannote-audio-eval registry={path_to_database.yml}
+                        protocol={protocol_name}
                         subset={test | development | train}
                         model={path_to_pretrained_model}
                         warm_up={warm_up_duration_in_seconds}