pysilero-vad 1.0.0__py3-none-any.whl

pysilero_vad/__init__.py

@@ -0,0 +1,60 @@
+import logging
+from pathlib import Path
+from typing import Final, Union
+
+import numpy as np
+import onnxruntime
+
+_RATE: Final = 16000
+_MAX_WAV: Final = 32767
+_DIR = Path(__file__).parent
+_DEFAULT_ONNX_PATH = _DIR / "models" / "silero_vad.onnx"
+
+_LOGGER = logging.getLogger()
+
+
+class SileroVoiceActivityDetector:
+    """Detects speech/silence using Silero VAD.
+
+    https://github.com/snakers4/silero-vad
+    """
+
+    def __init__(self, onnx_path: Union[str, Path] = _DEFAULT_ONNX_PATH) -> None:
+        onnx_path = str(onnx_path)
+
+        opts = onnxruntime.SessionOptions()
+        opts.inter_op_num_threads = 1
+        opts.intra_op_num_threads = 1
+
+        self.session = onnxruntime.InferenceSession(
+            onnx_path, providers=["CPUExecutionProvider"], sess_options=opts
+        )
+
+        self._h = np.zeros((2, 1, 64)).astype("float32")
+        self._c = np.zeros((2, 1, 64)).astype("float32")
+
+    def reset(self) -> None:
+        """Reset state."""
+        self._h = np.zeros((2, 1, 64)).astype("float32")
+        self._c = np.zeros((2, 1, 64)).astype("float32")
+
+    def __call__(self, audio: bytes) -> float:
+        """Return probability of speech in audio [0-1].
+
+        Audio must be 16Khz 16-bit mono PCM.
+        """
+        audio_array = np.frombuffer(audio, dtype=np.int16).astype(np.float32) / _MAX_WAV
+
+        # Add batch dimension
+        audio_array = np.expand_dims(audio_array, 0)
+
+        ort_inputs = {
+            "input": audio_array,
+            "h": self._h,
+            "c": self._c,
+            "sr": np.array(_RATE, dtype=np.int64),
+        }
+        ort_outs = self.session.run(None, ort_inputs)
+        out, self._h, self._c = ort_outs
+
+        return out.squeeze()

pysilero_vad-1.0.0.dist-info/LICENSE.md

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Michael Hansen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pysilero_vad-1.0.0.dist-info/METADATA

@@ -0,0 +1,43 @@
+Metadata-Version: 2.1
+Name: pysilero-vad
+Version: 1.0.0
+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
+License: MIT
+Keywords: voice activity vad
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+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
+Description-Content-Type: text/markdown
+License-File: LICENSE.md
+Requires-Dist: onnxruntime <2,>=1.10.0
+Requires-Dist: numpy <1.26
+
+# pySilero VAD
+
+A pre-packaged voice activity detector using [silero-vad](https://github.com/snakers4/silero-vad).
+
+``` sh
+pip install pysilero-vad
+```
+
+``` python
+from pysilero_vad import SileroVoiceActivityDetector
+
+vad = SileroVoiceActivityDetector()
+
+# Audio must be 16Khz, 16-bit mono PCM
+if vad(audio_bytes) >= 0.5:
+    print("Speech")
+else:
+    print("Silence")
+```
+

pysilero_vad-1.0.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+pysilero_vad/__init__.py,sha256=k0kb-HkhJwqD_O5YsOAQhV0Zbk7gnAy5XRTy2iiLQXY,1708
+pysilero_vad/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pysilero_vad/models/silero_vad.onnx,sha256=o16_Uv085fFGmyo2FY26dhvEe5c-ozgrMYbKFbH1ryg,1807522
+pysilero_vad-1.0.0.dist-info/LICENSE.md,sha256=E3RtUJ105V6iJl--8gS7fNv4SoMVsCB-mIMmy1Q4cCg,1071
+pysilero_vad-1.0.0.dist-info/METADATA,sha256=-0F8V6kxyed4OmFwVuJkSZ9lbvnvnmEny0INFxmnHbQ,1219
+pysilero_vad-1.0.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+pysilero_vad-1.0.0.dist-info/top_level.txt,sha256=QQlOVbq_uDMukkVxjBFRi8eOwSrzJDrbP8YY1MCeMIs,13
+pysilero_vad-1.0.0.dist-info/RECORD,,

pysilero_vad-1.0.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.42.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

pysilero_vad-1.0.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+pysilero_vad