akiki 0.0.1__tar.gz

akiki-0.0.1/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 [yyyy] [name of copyright owner]
+
+   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.

akiki-0.0.1/MANIFEST.in

@@ -0,0 +1,2 @@
+include LICENSE README.md
+recursive-include src/akiki/models *.onnx *.json *.md

akiki-0.0.1/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.4
+Name: akiki
+Version: 0.0.1
+Summary: Local streaming voice activity detection with Akiki VAD
+Author: Akiki AI
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://huggingface.co/Akiki-AI
+Keywords: vad,audio,speech,voice-activity-detection
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.24
+Requires-Dist: onnxruntime>=1.17
+Requires-Dist: soundfile>=0.12
+Dynamic: license-file
+
+# Akiki
+
+Run streaming voice activity detection locally with a small bundled Akiki VAD
+model. No model download, network connection or PyTorch is needed at runtime.
+
+```bash
+pip install akiki
+akiki --version
+akiki recording.wav
+```
+
+Audio must be mono at 16,000 Hz. The CLI prints one JSON object per complete
+16 ms frame: its start, end, speech probability and threshold decision.
+
+```python
+import soundfile as sf
+from akiki import VAD
+
+audio, sample_rate = sf.read("recording.wav", dtype="float32")
+vad = VAD()
+for frame in vad.push(audio, sample_rate=sample_rate):
+    print(frame)
+vad.reset()  # Start a new recording.
+```
+
+`push()` accepts arbitrary buffer sizes and retains incomplete frames between
+calls. A trailing incomplete frame is left pending; it is not padded or scored.
+Use `VAD(threshold=0.6)` or `akiki recording.wav --threshold 0.6` to change the
+threshold. Probabilities are always returned.
+
+Version 0.0.1 bundles the experimental **candidate-1, seed 1729** model, with
+210,561 parameters and a 16 ms output hop. It is an initial functional release;
+future versions will supply the production Akiki VAD models. Training provenance
+and checksums are included in `akiki/models/MODEL_CARD.md` and the model metadata.
+
+Code and bundled Akiki weights are provided under Apache-2.0. Source audio and
+the independent teacher retain their original licences; neither is distributed
+in this package.
+
+To publish this release from the project directory:
+
+```bash
+uv build
+uv publish dist/akiki-0.0.1*
+```
+
+Authenticate to PyPI locally when prompted. The project contains no credentials.

akiki-0.0.1/README.md

@@ -0,0 +1,47 @@
+# Akiki
+
+Run streaming voice activity detection locally with a small bundled Akiki VAD
+model. No model download, network connection or PyTorch is needed at runtime.
+
+```bash
+pip install akiki
+akiki --version
+akiki recording.wav
+```
+
+Audio must be mono at 16,000 Hz. The CLI prints one JSON object per complete
+16 ms frame: its start, end, speech probability and threshold decision.
+
+```python
+import soundfile as sf
+from akiki import VAD
+
+audio, sample_rate = sf.read("recording.wav", dtype="float32")
+vad = VAD()
+for frame in vad.push(audio, sample_rate=sample_rate):
+    print(frame)
+vad.reset()  # Start a new recording.
+```
+
+`push()` accepts arbitrary buffer sizes and retains incomplete frames between
+calls. A trailing incomplete frame is left pending; it is not padded or scored.
+Use `VAD(threshold=0.6)` or `akiki recording.wav --threshold 0.6` to change the
+threshold. Probabilities are always returned.
+
+Version 0.0.1 bundles the experimental **candidate-1, seed 1729** model, with
+210,561 parameters and a 16 ms output hop. It is an initial functional release;
+future versions will supply the production Akiki VAD models. Training provenance
+and checksums are included in `akiki/models/MODEL_CARD.md` and the model metadata.
+
+Code and bundled Akiki weights are provided under Apache-2.0. Source audio and
+the independent teacher retain their original licences; neither is distributed
+in this package.
+
+To publish this release from the project directory:
+
+```bash
+uv build
+uv publish dist/akiki-0.0.1*
+```
+
+Authenticate to PyPI locally when prompted. The project contains no credentials.

akiki-0.0.1/pyproject.toml

@@ -0,0 +1,36 @@
+[build-system]
+requires = ["setuptools>=77.0.3", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "akiki"
+version = "0.0.1"
+description = "Local streaming voice activity detection with Akiki VAD"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{name = "Akiki AI"}]
+keywords = ["vad", "audio", "speech", "voice-activity-detection"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Programming Language :: Python :: 3",
+  "Topic :: Multimedia :: Sound/Audio :: Analysis",
+]
+dependencies = ["numpy>=1.24", "onnxruntime>=1.17", "soundfile>=0.12"]
+
+[project.urls]
+Homepage = "https://huggingface.co/Akiki-AI"
+
+[project.scripts]
+akiki = "akiki.__main__:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+akiki = ["models/*.onnx", "models/*.json", "models/*.md"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+testpaths = ["tests"]

akiki-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

akiki-0.0.1/src/akiki/__init__.py

@@ -0,0 +1,5 @@
+"""Small, offline streaming voice activity detector."""
+from .vad import SpeechFrame, VAD
+
+__version__ = "0.0.1"
+__all__ = ["SpeechFrame", "VAD", "__version__"]

akiki-0.0.1/src/akiki/__main__.py

@@ -0,0 +1,29 @@
+from dataclasses import asdict
+import argparse
+import json
+
+from . import __version__
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Run Akiki VAD locally on mono 16 kHz audio.")
+    parser.add_argument("--version", action="version", version=f"akiki {__version__}")
+    parser.add_argument("audio", help="Input audio file")
+    parser.add_argument("--threshold", type=float, default=None)
+    args = parser.parse_args()
+    import soundfile as sf
+    from . import VAD
+    try:
+        detector = VAD(threshold=args.threshold)
+        with sf.SoundFile(args.audio) as source:
+            if source.samplerate != 16000 or source.channels != 1:
+                raise ValueError("Expected mono 16 kHz audio")
+            for block in source.blocks(blocksize=16000, dtype="float32"):
+                for frame in detector.push(block):
+                    print(json.dumps(asdict(frame)))
+    except (OSError, ValueError, RuntimeError) as error:
+        parser.exit(2, f"akiki: {error}\n")
+
+
+if __name__ == "__main__":
+    main()

akiki-0.0.1/src/akiki/models/MODEL_CARD.md

@@ -0,0 +1,22 @@
+# Bundled model: candidate-1, seed 1729
+
+Experimental Akiki CNN+GRU128, 210,561 parameters, FP32 ONNX with full waveform
+frontend and explicit recurrent state. Mono 16 kHz; 256 new samples per output
+(16 ms), with 320 past context samples. Threshold 0.5.
+
+Fresh random student initialization; independent cached Silero 6.2.3 soft
+teacher labels on approximately 994 hours of commercially permitted training
+audio. The cache retains 58 explicitly instrumental zero-label exceptions.
+Native 32 ms targets supervise the mean of two 16 ms student outputs.
+No TEN or Silero v5 supervision and no AMI/ICSI training audio.
+
+Selected at training window 24 in candidate-study-v1. That historical study used
+85% teacher and 15% AMI validation loss for checkpoint selection, including for
+candidate-1. AMI validation did not contribute gradients. This package freezes
+that existing candidate; it does not contain the subsequently requested rerun.
+
+Code and these Akiki weights: Apache-2.0, matching the Akiki repository licence.
+Silero VAD is MIT licensed: https://github.com/snakers4/silero-vad . No Silero
+weights or source audio are included. Dataset audio retains its original terms.
+
+ONNX SHA256: `80c2bc5761f29a4abf98420139d2be4975084d087b52278e1b91084299607c4c`.

akiki-0.0.1/src/akiki/models/candidate-1.json

@@ -0,0 +1,29 @@
+{
+  "bytes": 1117830,
+  "created_utc": "2026-10-24T20:07:21Z",
+  "input_policy": "576 samples = 320 past + 256 current; fixed batch 1, 16kHz; complete frontend included",
+  "onnx_sha256": "80c2bc5761f29a4abf98420139d2be4975084d087b52278e1b91084299607c4c",
+  "origin": {
+    "checkpoint_sha256": "bc0feb888b8cea73678acc7bc3a4b02c1f1d90f266c7b77431565f55a63c849b",
+    "family": "candidate-1",
+    "human_test_checkpoint_selection": false,
+    "published_ami_icsi_annotations_used": false,
+    "recipe_sha256": "77a1f2865008125866ffb811b1fe66c1b0582fc848cb149a1931810c29e7fa0f",
+    "seed": 1729,
+    "teacher_release": "6.2.3",
+    "teacher_sha256": "1a153a22f4509e292a94e67d6f9b85e8deb25b4988682b7e174c65279d8788e3",
+    "teacher_v5_supervision_used": false,
+    "ten_supervision_used": false,
+    "threshold_source": "Frozen0.5; same validation rule across all families; no benchmark threshold tuning"
+  },
+  "spec": {
+    "chunk_samples": 256,
+    "context_samples": 320,
+    "frontend": "Silero-v5-16k",
+    "hidden": 128,
+    "kind": "gru",
+    "sample_rate": 16000
+  },
+  "threshold": 0.5,
+  "threshold_source": "Frozen0.5; same validation rule across all families; no benchmark threshold tuning"
+}

akiki-0.0.1/src/akiki/vad.py

@@ -0,0 +1,73 @@
+"""CPU ONNX inference for the bundled full-waveform Akiki model."""
+from __future__ import annotations
+
+from dataclasses import dataclass
+import hashlib
+import json
+from pathlib import Path
+
+import numpy as np
+
+SAMPLE_RATE = 16000
+
+
+@dataclass(frozen=True)
+class SpeechFrame:
+    start_seconds: float
+    end_seconds: float
+    probability: float
+    speech: bool
+
+
+class VAD:
+    """Stateful 16 kHz mono VAD. Call reset() between recordings."""
+
+    def __init__(self, model_path: str | Path | None = None, threshold: float | None = None):
+        import onnxruntime as ort
+        path = Path(model_path) if model_path is not None else Path(__file__).parent / "models/candidate-1.onnx"
+        metadata = json.loads(path.with_suffix(".json").read_text())
+        if hashlib.sha256(path.read_bytes()).hexdigest() != metadata["onnx_sha256"]:
+            raise ValueError("Model checksum does not match its metadata")
+        spec = metadata["spec"]
+        self.chunk_samples = int(spec["chunk_samples"])
+        self.context_samples = int(spec["context_samples"])
+        self.hidden = int(spec["hidden"])
+        if spec["kind"] != "gru" or (self.chunk_samples, self.context_samples) not in {(256, 320), (512, 64)}:
+            raise ValueError("Expected an Akiki full-waveform GRU ONNX model")
+        self.threshold = float(metadata["threshold"] if threshold is None else threshold)
+        if not np.isfinite(self.threshold) or not 0 <= self.threshold <= 1:
+            raise ValueError("Threshold must lie between zero and one")
+        options = ort.SessionOptions()
+        options.intra_op_num_threads = options.inter_op_num_threads = 1
+        self.session = ort.InferenceSession(str(path), sess_options=options, providers=["CPUExecutionProvider"])
+        if {v.name for v in self.session.get_inputs()} != {"audio_with_context", "h"}:
+            raise ValueError("Unexpected ONNX inputs")
+        self.reset()
+
+    def reset(self) -> None:
+        self.context = np.zeros(self.context_samples, dtype=np.float32)
+        self.state = np.zeros((1, 1, self.hidden), dtype=np.float32)
+        self.pending = np.empty(0, dtype=np.float32)
+        self.completed_samples = 0
+
+    def push(self, samples, sample_rate: int = SAMPLE_RATE) -> list[SpeechFrame]:
+        audio = np.asarray(samples, dtype=np.float32)
+        if sample_rate != SAMPLE_RATE or audio.ndim != 1 or not np.isfinite(audio).all():
+            raise ValueError("Expected finite mono 16 kHz audio samples")
+        audio = np.concatenate([self.pending, audio])
+        complete = len(audio) // self.chunk_samples * self.chunk_samples
+        frames = []
+        for start in range(0, complete, self.chunk_samples):
+            window = np.concatenate([self.context, audio[start:start + self.chunk_samples]])
+            probability, state = self.session.run(None, {"audio_with_context": window[None], "h": self.state})
+            probability = float(np.asarray(probability).reshape(-1)[0])
+            if not np.isfinite(probability) or not 0 <= probability <= 1:
+                raise RuntimeError("Model returned an invalid speech probability")
+            begin = self.completed_samples
+            self.state = state
+            self.context = window[-self.context_samples:].copy()
+            self.completed_samples += self.chunk_samples
+            frames.append(SpeechFrame(begin / SAMPLE_RATE, self.completed_samples / SAMPLE_RATE,
+                                      probability, probability >= self.threshold))
+        self.pending = audio[complete:].copy()
+        return frames

akiki-0.0.1/src/akiki.egg-info/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.4
+Name: akiki
+Version: 0.0.1
+Summary: Local streaming voice activity detection with Akiki VAD
+Author: Akiki AI
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://huggingface.co/Akiki-AI
+Keywords: vad,audio,speech,voice-activity-detection
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.24
+Requires-Dist: onnxruntime>=1.17
+Requires-Dist: soundfile>=0.12
+Dynamic: license-file
+
+# Akiki
+
+Run streaming voice activity detection locally with a small bundled Akiki VAD
+model. No model download, network connection or PyTorch is needed at runtime.
+
+```bash
+pip install akiki
+akiki --version
+akiki recording.wav
+```
+
+Audio must be mono at 16,000 Hz. The CLI prints one JSON object per complete
+16 ms frame: its start, end, speech probability and threshold decision.
+
+```python
+import soundfile as sf
+from akiki import VAD
+
+audio, sample_rate = sf.read("recording.wav", dtype="float32")
+vad = VAD()
+for frame in vad.push(audio, sample_rate=sample_rate):
+    print(frame)
+vad.reset()  # Start a new recording.
+```
+
+`push()` accepts arbitrary buffer sizes and retains incomplete frames between
+calls. A trailing incomplete frame is left pending; it is not padded or scored.
+Use `VAD(threshold=0.6)` or `akiki recording.wav --threshold 0.6` to change the
+threshold. Probabilities are always returned.
+
+Version 0.0.1 bundles the experimental **candidate-1, seed 1729** model, with
+210,561 parameters and a 16 ms output hop. It is an initial functional release;
+future versions will supply the production Akiki VAD models. Training provenance
+and checksums are included in `akiki/models/MODEL_CARD.md` and the model metadata.
+
+Code and bundled Akiki weights are provided under Apache-2.0. Source audio and
+the independent teacher retain their original licences; neither is distributed
+in this package.
+
+To publish this release from the project directory:
+
+```bash
+uv build
+uv publish dist/akiki-0.0.1*
+```
+
+Authenticate to PyPI locally when prompted. The project contains no credentials.

akiki-0.0.1/src/akiki.egg-info/SOURCES.txt

@@ -0,0 +1,17 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+src/akiki/__init__.py
+src/akiki/__main__.py
+src/akiki/vad.py
+src/akiki.egg-info/PKG-INFO
+src/akiki.egg-info/SOURCES.txt
+src/akiki.egg-info/dependency_links.txt
+src/akiki.egg-info/entry_points.txt
+src/akiki.egg-info/requires.txt
+src/akiki.egg-info/top_level.txt
+src/akiki/models/MODEL_CARD.md
+src/akiki/models/candidate-1.json
+src/akiki/models/candidate-1.onnx
+tests/test_vad.py

akiki-0.0.1/src/akiki.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

akiki-0.0.1/src/akiki.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+akiki = akiki.__main__:main

akiki-0.0.1/src/akiki.egg-info/requires.txt

@@ -0,0 +1,3 @@
+numpy>=1.24
+onnxruntime>=1.17
+soundfile>=0.12

akiki-0.0.1/src/akiki.egg-info/top_level.txt

@@ -0,0 +1 @@
+akiki

akiki-0.0.1/tests/test_vad.py

@@ -0,0 +1,33 @@
+import numpy as np
+import pytest
+from akiki import VAD
+
+
+def test_streaming_matches_one_shot_and_reset():
+    audio = np.random.default_rng(1729).normal(0, .02, 256 * 9 + 71).astype(np.float32)
+    detector = VAD()
+    expected = detector.push(audio)
+    assert len(expected) == 9 and len(detector.pending) == 71
+    detector.reset()
+    actual = [f for i in range(0, len(audio), 173) for f in detector.push(audio[i:i+173])]
+    assert actual == expected
+    assert actual[0].start_seconds == 0 and actual[-1].end_seconds == .144
+    detector.reset()
+    assert detector.push(audio) == expected
+
+
+def test_invalid_audio_does_not_mutate_state():
+    detector = VAD()
+    detector.push(np.zeros(37, np.float32))
+    before = detector.pending.copy(), detector.state.copy(), detector.context.copy()
+    for audio, rate in [(np.zeros(20), 8000), (np.zeros((20, 2)), 16000), (np.array([np.nan]), 16000)]:
+        with pytest.raises(ValueError):
+            detector.push(audio, rate)
+    for actual, expected in zip((detector.pending, detector.state, detector.context), before):
+        np.testing.assert_array_equal(actual, expected)
+
+
+def test_threshold_range():
+    for threshold in [-.1, 1.1, float('nan')]:
+        with pytest.raises(ValueError, match="Threshold"):
+            VAD(threshold=threshold)