pysilero-vad 2.0.0__tar.gz → 2.1.0__tar.gz

{pysilero_vad-2.0.0 → pysilero_vad-2.1.0}/PKG-INFO

@@ -1,25 +1,28 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: pysilero_vad
-Version: 2.0.0
+Version: 2.1.0
 Summary: Pre-packaged voice activity detector using silero-vad
-Home-page: http://github.com/rhasspy/pysilero-vad
-Author: Michael Hansen
-Author-email: mike@rhasspy.org
+Author-email: Michael Hansen <mike@rhasspy.org>
 License: MIT
-Keywords: voice activity vad
+Project-URL: Source Code, http://github.com/rhasspy/pysilero-vad
+Keywords: voice,activity,vad
+Platform: any
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
-Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Text Processing :: Linguistic
 Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.8.0
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
 Requires-Dist: onnxruntime<2,>=1.18.0
-Requires-Dist: numpy<2
+Requires-Dist: numpy
+Dynamic: license-file
 
 # pySilero VAD
 
@@ -34,7 +37,10 @@ from pysilero_vad import SileroVoiceActivityDetector
 
 vad = SileroVoiceActivityDetector()
 
-# Audio must be 16Khz, 16-bit mono PCM
+# Audio must be 16Khz, 16-bit mono PCM with correct chunk size
+# See also: vad.chunk_samples()
+assert len(audio_bytes) == vad.chunk_bytes()
+
 if vad(audio_bytes) >= 0.5:
     print("Speech")
 else:

{pysilero_vad-2.0.0 → pysilero_vad-2.1.0}/README.md

@@ -11,7 +11,10 @@ from pysilero_vad import SileroVoiceActivityDetector
 
 vad = SileroVoiceActivityDetector()
 
-# Audio must be 16Khz, 16-bit mono PCM
+# Audio must be 16Khz, 16-bit mono PCM with correct chunk size
+# See also: vad.chunk_samples()
+assert len(audio_bytes) == vad.chunk_bytes()
+
 if vad(audio_bytes) >= 0.5:
     print("Speech")
 else:

pysilero_vad-2.1.0/pyproject.toml

@@ -0,0 +1,46 @@
+[build-system]
+requires = ["setuptools>=62.3"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name        = "pysilero_vad"
+version     = "2.1.0"
+license     = {text = "MIT"}
+description = "Pre-packaged voice activity detector using silero-vad"
+readme      = "README.md"
+authors     = [
+    {name = "Michael Hansen", email = "mike@rhasspy.org"}
+]
+keywords    = ["voice", "activity", "vad"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Topic :: Text Processing :: Linguistic",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+requires-python = ">=3.8.0"
+dependencies = [
+    "onnxruntime>=1.18.0,<2",
+    "numpy",
+]
+
+[project.urls]
+"Source Code" = "http://github.com/rhasspy/pysilero-vad"
+
+[tool.setuptools]
+platforms = ["any"]
+zip-safe  = true
+include-package-data = true
+
+[tool.setuptools.packages.find]
+include = ["pysilero_vad"]
+exclude = ["tests", "tests.*"]
+
+[tool.setuptools.package-data]
+pysilero_vad = ["models/silero_vad.onnx"]

{pysilero_vad-2.0.0 → pysilero_vad-2.1.0}/pysilero_vad/__init__.py

@@ -73,6 +73,17 @@ class SileroVoiceActivityDetector:
 
         audio_array = np.frombuffer(audio, dtype=np.int16).astype(np.float32) / _MAX_WAV
 
+        return self.process_array(audio_array)
+
+    def process_array(self, audio_array: np.ndarray) -> float:
+        """Return probability of speech [0-1] in a single audio chunk.
+
+        Audio *must* be 512 float samples [0-1] of 16Khz mono.
+        """
+        if len(audio_array) != _CHUNK_SAMPLES:
+            # Window size is fixed at 512 samples in v5
+            raise InvalidChunkSizeError
+
         # Add batch dimension and context
         audio_array = np.concatenate(
             (self._context, audio_array[np.newaxis, :]), axis=1

{pysilero_vad-2.0.0 → pysilero_vad-2.1.0}/pysilero_vad.egg-info/PKG-INFO

@@ -1,25 +1,28 @@
-Metadata-Version: 2.1
-Name: pysilero-vad
-Version: 2.0.0
+Metadata-Version: 2.4
+Name: pysilero_vad
+Version: 2.1.0
 Summary: Pre-packaged voice activity detector using silero-vad
-Home-page: http://github.com/rhasspy/pysilero-vad
-Author: Michael Hansen
-Author-email: mike@rhasspy.org
+Author-email: Michael Hansen <mike@rhasspy.org>
 License: MIT
-Keywords: voice activity vad
+Project-URL: Source Code, http://github.com/rhasspy/pysilero-vad
+Keywords: voice,activity,vad
+Platform: any
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
-Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Text Processing :: Linguistic
 Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.8.0
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
 Requires-Dist: onnxruntime<2,>=1.18.0
-Requires-Dist: numpy<2
+Requires-Dist: numpy
+Dynamic: license-file
 
 # pySilero VAD
 
@@ -34,7 +37,10 @@ from pysilero_vad import SileroVoiceActivityDetector
 
 vad = SileroVoiceActivityDetector()
 
-# Audio must be 16Khz, 16-bit mono PCM
+# Audio must be 16Khz, 16-bit mono PCM with correct chunk size
+# See also: vad.chunk_samples()
+assert len(audio_bytes) == vad.chunk_bytes()
+
 if vad(audio_bytes) >= 0.5:
     print("Speech")
 else:

{pysilero_vad-2.0.0 → pysilero_vad-2.1.0}/pysilero_vad.egg-info/SOURCES.txt

@@ -1,9 +1,7 @@
 LICENSE.md
-MANIFEST.in
 README.md
-requirements.txt
+pyproject.toml
 setup.cfg
-setup.py
 pysilero_vad/__init__.py
 pysilero_vad/py.typed
 pysilero_vad.egg-info/PKG-INFO
@@ -11,5 +9,6 @@ pysilero_vad.egg-info/SOURCES.txt
 pysilero_vad.egg-info/dependency_links.txt
 pysilero_vad.egg-info/requires.txt
 pysilero_vad.egg-info/top_level.txt
+pysilero_vad.egg-info/zip-safe
 pysilero_vad/models/silero_vad.onnx
 tests/test_vad.py

{pysilero_vad-2.0.0 → pysilero_vad-2.1.0}/pysilero_vad.egg-info/requires.txt

@@ -1,2 +1,2 @@
 onnxruntime<2,>=1.18.0
-numpy<2
+numpy

pysilero_vad-2.1.0/pysilero_vad.egg-info/zip-safe

@@ -0,0 +1 @@
+

{pysilero_vad-2.0.0 → pysilero_vad-2.1.0}/tests/test_vad.py

@@ -2,8 +2,10 @@ import wave
 from pathlib import Path
 from typing import Union
 
+import numpy as np
 import pytest
-from pysilero_vad import SileroVoiceActivityDetector, InvalidChunkSizeError
+
+from pysilero_vad import InvalidChunkSizeError, SileroVoiceActivityDetector
 
 _DIR = Path(__file__).parent
 
@@ -29,12 +31,16 @@ def test_speech() -> None:
     vad = SileroVoiceActivityDetector()
     assert any(p >= 0.5 for p in vad.process_chunks(_load_wav(_DIR / "speech.wav")))
 
+
 def test_invalid_chunk_size() -> None:
     """Test that chunk size must be 512 samples."""
     vad = SileroVoiceActivityDetector()
 
     # Should work
     vad(bytes(SileroVoiceActivityDetector.chunk_bytes()))
+    vad.process_array(
+        np.zeros(SileroVoiceActivityDetector.chunk_samples(), dtype=np.float32)
+    )
 
     # Should fail
     with pytest.raises(InvalidChunkSizeError):
@@ -42,3 +48,13 @@ def test_invalid_chunk_size() -> None:
 
     with pytest.raises(InvalidChunkSizeError):
         vad(bytes(SileroVoiceActivityDetector.chunk_bytes() // 2))
+
+    with pytest.raises(InvalidChunkSizeError):
+        vad.process_array(
+            np.zeros(SileroVoiceActivityDetector.chunk_samples() * 2, dtype=np.float32)
+        )
+
+    with pytest.raises(InvalidChunkSizeError):
+        vad.process_array(
+            np.zeros(SileroVoiceActivityDetector.chunk_samples() // 2, dtype=np.float32)
+        )

pysilero_vad-2.0.0/MANIFEST.in

@@ -1,2 +0,0 @@
-include requirements.txt
-include pysilero_vad/models/*.onnx

pysilero_vad-2.0.0/requirements.txt

@@ -1,2 +0,0 @@
-onnxruntime>=1.18.0,<2
-numpy<2

pysilero_vad-2.0.0/setup.py

@@ -1,53 +0,0 @@
-#!/usr/bin/env python3
-from pathlib import Path
-
-import setuptools
-from setuptools import setup
-
-this_dir = Path(__file__).parent
-module_dir = this_dir / "pysilero_vad"
-
-# -----------------------------------------------------------------------------
-
-# Load README in as long description
-long_description: str = ""
-readme_path = this_dir / "README.md"
-if readme_path.is_file():
-    long_description = readme_path.read_text(encoding="utf-8")
-
-requirements = []
-requirements_path = this_dir / "requirements.txt"
-if requirements_path.is_file():
-    with open(requirements_path, "r", encoding="utf-8") as requirements_file:
-        requirements = requirements_file.read().splitlines()
-
-# -----------------------------------------------------------------------------
-
-setup(
-    name="pysilero_vad",
-    version="2.0.0",
-    description="Pre-packaged voice activity detector using silero-vad",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    url="http://github.com/rhasspy/pysilero-vad",
-    author="Michael Hansen",
-    author_email="mike@rhasspy.org",
-    license="MIT",
-    packages=setuptools.find_packages(),
-    package_data={
-        "pysilero_vad": ["py.typed", "models/silero_vad.onnx"],
-    },
-    install_requires=requirements,
-    classifiers=[
-        "Development Status :: 3 - Alpha",
-        "Intended Audience :: Developers",
-        "Topic :: Multimedia :: Sound/Audio :: Speech",
-        "License :: OSI Approved :: MIT License",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
-        "Programming Language :: Python :: 3.11",
-    ],
-    keywords="voice activity vad",
-)