cjm-capability-pyannote 0.0.3__tar.gz

cjm_capability_pyannote-0.0.3/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2022, fastai
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cjm_capability_pyannote-0.0.3/PKG-INFO

@@ -0,0 +1,42 @@
+Metadata-Version: 2.4
+Name: cjm-capability-pyannote
+Version: 0.0.3
+Summary: A pyannote.audio speaker-diarization capability for the cjm-substrate runtime — source audio in, anonymous time-ranged speaker turns out (community-1 pipeline by default; HF-gated). Identity stays downstream human judgment: the correction TUI's assignment lane.
+Author-email: "Christian J. Mills" <9126128+cj-mills@users.noreply.github.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/cj-mills/cjm-capability-pyannote
+Classifier: Natural Language :: English
+Classifier: Intended Audience :: Developers
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjm-substrate>=0.0.58
+Requires-Dist: cjm-capability-primitives>=0.0.12
+Requires-Dist: cjm-substrate-torch-utils
+Requires-Dist: pyannote.audio>=4.0
+Dynamic: license-file
+
+# cjm-capability-pyannote
+
+<!-- generated from the context graph by `cjm-context-graph readme` — do not edit by hand; edit the graph (the urge to hand-edit = move it on-graph) -->
+
+Speaker-diarization capability backed by pyannote.audio (community-1) — full-source decoded-PCM audio → time-ranged anonymous speaker turns (SPEAKER_00-style cluster labels, never identities), implementing the speaker-diarization adapter interface; pure compute — caching lives in the generic adapter. Default-on rung in the transcription workflow; the correction TUI's assign lane consumes the turns.
+
+## Modules
+
+- **`cjm_capability_pyannote.__init__`**
+- **`cjm_capability_pyannote.capability`** — Speaker-diarization tool capability using pyannote.audio (session-D DECs 18d7de80 + d6df3a8e): source audio in, ANONYMOUS time-ranged speaker turns out — the machine half of speaker assignment; identity stays the correction TUI's human lane (DEC 44afb2df).
+
+## API
+
+### `cjm_capability_pyannote.capability`
+
+- `PyannoteConfig` _class_ — Configuration for the pyannote diarization pipeline.
+- `PyannoteDiarizationCapability` _class_ — Speaker-diarization tool capability wrapping a pyannote.audio Pipeline.
+
+## Dependencies
+
+**Depends on:** `cjm-capability-primitives`, `cjm-substrate`, `cjm-substrate-torch-utils`, `pyannote.audio`

cjm_capability_pyannote-0.0.3/README.md

@@ -0,0 +1,21 @@
+# cjm-capability-pyannote
+
+<!-- generated from the context graph by `cjm-context-graph readme` — do not edit by hand; edit the graph (the urge to hand-edit = move it on-graph) -->
+
+Speaker-diarization capability backed by pyannote.audio (community-1) — full-source decoded-PCM audio → time-ranged anonymous speaker turns (SPEAKER_00-style cluster labels, never identities), implementing the speaker-diarization adapter interface; pure compute — caching lives in the generic adapter. Default-on rung in the transcription workflow; the correction TUI's assign lane consumes the turns.
+
+## Modules
+
+- **`cjm_capability_pyannote.__init__`**
+- **`cjm_capability_pyannote.capability`** — Speaker-diarization tool capability using pyannote.audio (session-D DECs 18d7de80 + d6df3a8e): source audio in, ANONYMOUS time-ranged speaker turns out — the machine half of speaker assignment; identity stays the correction TUI's human lane (DEC 44afb2df).
+
+## API
+
+### `cjm_capability_pyannote.capability`
+
+- `PyannoteConfig` _class_ — Configuration for the pyannote diarization pipeline.
+- `PyannoteDiarizationCapability` _class_ — Speaker-diarization tool capability wrapping a pyannote.audio Pipeline.
+
+## Dependencies
+
+**Depends on:** `cjm-capability-primitives`, `cjm-substrate`, `cjm-substrate-torch-utils`, `pyannote.audio`

cjm_capability_pyannote-0.0.3/cjm_capability_pyannote/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.3"

cjm_capability_pyannote-0.0.3/cjm_capability_pyannote/capability.py

@@ -0,0 +1,231 @@
+"""Speaker-diarization tool capability using pyannote.audio (session-D DECs 18d7de80 + d6df3a8e): source audio in, ANONYMOUS time-ranged speaker turns out — the machine half of speaker assignment; identity stays the correction TUI's human lane (DEC 44afb2df)."""
+
+import logging
+import os
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional
+
+from cjm_capability_primitives.speaker_diarization import SpeakerDiarizationResult, SpeakerTurn
+from cjm_substrate.core.capability import RELOAD_TRIGGER, ToolCapability
+from cjm_substrate.core.errors import CapabilityFatalError, CapabilityInputError
+from cjm_substrate.utils.validation import (config_to_dict, dataclass_to_jsonschema, dict_to_config,
+                                            SCHEMA_DESC, SCHEMA_TITLE)
+from cjm_substrate_torch_utils.memory import release_model
+
+# The tool wraps a pyannote.audio Pipeline (community-1 by default). Models are
+# HF-GATED: accepting the model's user conditions + a HuggingFace token are ENV
+# PROVISIONING facts (hf auth login, or HF_TOKEN/HUGGING_FACE_HUB_TOKEN in the
+# worker env) — never config knobs. First diarize() downloads the pipeline into
+# the standard HF cache.
+
+# pyannote Imports
+try:
+    import torch
+    from pyannote.audio import Pipeline
+    PYANNOTE_AVAILABLE = True
+except ImportError:
+    PYANNOTE_AVAILABLE = False
+
+
+@dataclass
+class PyannoteConfig:
+    """Configuration for the pyannote diarization pipeline.
+
+    Speaker-count hints are deliberately NOT config fields: they are
+    per-CALL knowledge (`diarize(..., num_speakers=2)`) — how many people sat
+    in one recording is a property of the source, not of the tool."""
+
+    model_id: str = field(
+        default="pyannote/speaker-diarization-community-1",
+        metadata={
+            SCHEMA_TITLE: "Model ID",
+            SCHEMA_DESC: "HuggingFace pipeline id (gated: accept the model's user "
+                         "conditions and provision a token in the worker env).",
+            RELOAD_TRIGGER: "pipeline",  # a model change invalidates the loaded pipeline
+        }
+    )
+    device: str = field(
+        default="auto",
+        metadata={
+            SCHEMA_TITLE: "Device",
+            SCHEMA_DESC: "Torch device for the pipeline: 'auto' (cuda when available), "
+                         "'cuda', 'cuda:N', or 'cpu'.",
+            RELOAD_TRIGGER: "pipeline",  # a device change invalidates the loaded pipeline
+        }
+    )
+
+
+class PyannoteDiarizationCapability(ToolCapability):
+    """Speaker-diarization tool capability wrapping a pyannote.audio Pipeline.
+
+    Native-surface model (PILLAR 1c): `diarize` runs the pretrained pipeline
+    over the caller's ORIGINAL source audio and returns typed `SpeakerTurn`s
+    in that audio's coordinates, time-ordered; overlapping turns are signal
+    (overlapped speech), not an error. Cluster labels (SPEAKER_00, ...) are
+    result-scoped — the assignment lane's cluster-name-once verdict binds
+    them to identities (DEC 8a4df244). The generic adapter
+    (cjm-speaker-diarization-adapter-interface) is a thin pass-through."""
+
+    config_class = PyannoteConfig
+
+    def __init__(self):
+        """Initialize the pyannote diarization capability."""
+        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+        self.config: Optional[PyannoteConfig] = None
+        self._pipeline = None
+        self._loaded_device: Optional[str] = None
+
+    @property
+    def name(self) -> str:  # Capability name identifier
+        """Capability identity, derived from the installed distribution (PILLAR 1c)."""
+        from importlib.metadata import metadata, packages_distributions
+        dist = (packages_distributions().get(__package__) or [__package__.replace("_", "-")])[0]
+        return metadata(dist)["Name"]
+
+    @property
+    def version(self) -> str:  # Capability version string
+        """Get the capability version string."""
+        from cjm_capability_pyannote import __version__
+        return __version__
+
+    def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
+        """Return current configuration state."""
+        return config_to_dict(self.config) if self.config else {}
+
+    def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for configuration
+        """Return JSON Schema for UI generation."""
+        return dataclass_to_jsonschema(PyannoteConfig)
+
+    def _apply_config(
+        self,
+        config: Optional[Any] = None  # Configuration dataclass, dict, or None
+    ) -> None:
+        """Apply config values only (no heavy-resource work). Called by
+        initialize (first-time) and by the substrate's reconfigure delta path."""
+        self.config = dict_to_config(PyannoteConfig, config or {})
+
+    def initialize(
+        self,
+        config: Optional[Any] = None  # Configuration dataclass, dict, or None
+    ) -> None:
+        """First-time setup. Config application is factored into _apply_config;
+        the substrate's reconfigure(old, new) fires _release_pipeline on a
+        model_id/device change (RELOAD_TRIGGER) then re-applies config."""
+        self._apply_config(config)
+        self.logger.info(f"Initialized pyannote diarization capability "
+                         f"(model={self.config.model_id}, device={self.config.device})")
+
+    @staticmethod
+    def _hf_token() -> Optional[str]:
+        """The HF token from the worker env (gated-model pull); None falls back
+        to the hub's cached login (hf auth login) — provisioning, not config."""
+        return os.environ.get("HF_TOKEN") or os.environ.get("HUGGING_FACE_HUB_TOKEN")
+
+    def _load_pipeline(self) -> None:
+        """Lazily load the pretrained pipeline and move it to the resolved device.
+
+        Gated-model failures (no token / conditions not accepted) surface as
+        CapabilityFatalError pointing at the provisioning fix — the operator
+        acts in the ENV, not in config."""
+        if self._pipeline is not None:
+            return
+        if not PYANNOTE_AVAILABLE:
+            raise CapabilityFatalError(  # load-time dependency missing — fatal until operator installs pyannote.audio
+                "pyannote.audio not installed.",
+            )
+        device = self.config.device
+        if device == "auto":
+            device = "cuda" if torch.cuda.is_available() else "cpu"
+        self.logger.info(f"Loading pipeline {self.config.model_id} on {device}")
+        try:
+            pipeline = Pipeline.from_pretrained(self.config.model_id,
+                                                token=self._hf_token())
+        except Exception as e:
+            raise CapabilityFatalError(
+                f"Failed to load {self.config.model_id!r}: {e} — gated model? "
+                "Accept the model's user conditions on huggingface.co and provision "
+                "a token in the worker env (hf auth login, or HF_TOKEN).",
+            ) from e
+        if pipeline is None:
+            raise CapabilityFatalError(
+                f"Pipeline.from_pretrained returned None for {self.config.model_id!r} "
+                "— the model is gated: accept its user conditions and provision a token.",
+            )
+        self._pipeline = pipeline.to(torch.device(device))
+        self._loaded_device = device
+
+    def _release_pipeline(self) -> None:
+        """Release the loaded pipeline (GPU memory back). RELOAD_TRIGGER target
+        for model_id/device; on_disable / cleanup delegate here."""
+        release_model(self, ["_pipeline"], device="cuda", logger=self.logger)
+        self._pipeline = None
+        self._loaded_device = None
+
+    HINT_KEYS = ("num_speakers", "min_speakers", "max_speakers")  # Per-call speaker-count hints read from kwargs
+
+    def diarize(
+        self,
+        audio: str,  # Path to the source audio to diarize (turn times index into THIS audio)
+        **kwargs     # Speaker-count hints (num_speakers/min_speakers/max_speakers) + provenance pass-through
+    ) -> SpeakerDiarizationResult:  # Time-ordered anonymous speaker turns
+        """Diarize source audio into time-ordered anonymous speaker turns.
+
+        The signature is `(audio, **kwargs)` to CONFORM TO THE PROTOCOL under
+        the substrate's surface-match PREFIX RULE (adapter binding compares
+        param lists; named params between `audio` and `**kwargs` break the
+        match — caught live 2026-07-26: the worker bound NO adapter). The
+        speaker-count hints are read from kwargs by name, the whisper/pysbd
+        family convention. Iterates the pipeline output via
+        `itertracks(yield_label=True)` — the stable surface across
+        pyannote.audio 3.x (bare Annotation) and 4.x
+        (DiarizeOutput.speaker_diarization). Turns keep source coordinates;
+        overlapping turns pass through untouched (overlapped speech is
+        signal the downstream join wants)."""
+        if not isinstance(audio, str) or not audio:
+            raise CapabilityInputError(  # typed input-validation
+                f"Unsupported audio input: {audio!r}; expected a non-empty path string",
+                fields_invalid=["audio"],
+            )
+        if not os.path.exists(audio):
+            raise CapabilityInputError(
+                f"Audio path does not exist: {audio}",
+                fields_invalid=["audio"],
+            )
+        self._load_pipeline()
+
+        hints = {k: kwargs[k] for k in self.HINT_KEYS if kwargs.get(k) is not None}
+        output = self._pipeline(audio, **hints)
+        annotation = getattr(output, "speaker_diarization", output)
+        turns: List[SpeakerTurn] = [
+            SpeakerTurn(start=float(segment.start), end=float(segment.end),
+                        speaker=str(label))
+            for segment, _track, label in annotation.itertracks(yield_label=True)
+        ]
+        turns.sort(key=lambda t: (t.start, t.end))
+        return SpeakerDiarizationResult(
+            turns=turns,
+            metadata={
+                "model_id": self.config.model_id,
+                "device": self._loaded_device,
+                "speaker_count": len({t.speaker for t in turns}),
+                "turn_count": len(turns),
+                **({"hints": hints} if hints else {}),
+            },
+        )
+
+    def is_available(self) -> bool:  # True if pyannote.audio is importable
+        """Check if pyannote.audio is available."""
+        return PYANNOTE_AVAILABLE
+
+    def prefetch(self) -> None:
+        """Eagerly load the pipeline (model download + device move) so the
+        first diarize() doesn't pay the cold-load cost."""
+        self._load_pipeline()
+
+    def on_disable(self) -> None:
+        """Release the pipeline when the operator disables the capability (worker stays alive)."""
+        self._release_pipeline()
+
+    def cleanup(self) -> None:
+        """Release resources on unload."""
+        self._release_pipeline()