Merge pull request #493 from snakers4/adamnsandle

Adamnsandle

README.md

@@ -25,6 +25,34 @@ https://user-images.githubusercontent.com/36505480/144874384-95f80f6d-a4f1-42cc-
 </details>
 
 <br/>
+
+<h2 align="center">Fast start</h2>
+<br/>
+
+**Using pip**:
+`pip install silero-vad`
+
+```python3
+from silero_vad import load_silero_vad, read_audio, get_speech_timestamps
+model = load_silero_vad()
+wav = read_audio('path_to_audio_file') # backend (sox, soundfile, or ffmpeg) required!
+speech_timestamps = get_speech_timestamps(wav, model)
+```
+
+**Using torch.hub**:
+```python3
+import torch
+torch.set_num_threads(1)
+
+model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad', model='silero_vad')
+(get_speech_timestamps, _, read_audio, _, _) = utils
+
+wav = read_audio('path_to_audio_file') # backend (sox, soundfile, or ffmpeg) required!
+speech_timestamps = get_speech_timestamps(wav, model)
+```
+
+<br/>
+
 <h2 align="center">Key Features</h2>
 <br/>
 
@@ -57,21 +85,7 @@ https://user-images.githubusercontent.com/36505480/144874384-95f80f6d-a4f1-42cc-
    Published under permissive license (MIT) Silero VAD has zero strings attached - no telemetry, no keys, no registration, no built-in expiration, no keys or vendor lock.
 
 <br/>
-<h2 align="center">Fast start</h2>
-<br/>
 
-```python3
-import torch
-torch.set_num_threads(1)
-
-model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad', model='silero_vad')
-(get_speech_timestamps, _, read_audio, _, _) = utils
-
-wav = read_audio('path_to_audio_file')
-speech_timestamps = get_speech_timestamps(wav, model)
-```
-
-<br/>
 <h2 align="center">Typical Use Cases</h2>
 <br/>
 

hubconf.py

@@ -1,16 +1,15 @@
 dependencies = ['torch', 'torchaudio']
 import torch
-import json
 import os
-from utils_vad import (init_jit_model,
-                       get_speech_timestamps,
-                       save_audio,
-                       read_audio,
-                       VADIterator,
-                       collect_chunks,
-                       drop_chunks,
-                       Validator,
-                       OnnxWrapper)
+import sys
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'src'))
+from silero_vad.utils_vad import (init_jit_model,
+                                  get_speech_timestamps,
+                                  save_audio,
+                                  read_audio,
+                                  VADIterator,
+                                  collect_chunks,
+                                  OnnxWrapper)
 
 
 def versiontuple(v):
@@ -36,7 +35,7 @@ def silero_vad(onnx=False, force_onnx_cpu=False):
         if versiontuple(installed_version) < versiontuple(supported_version):
             raise Exception(f'Please install torch {supported_version} or greater ({installed_version} installed)')
 
-    model_dir = os.path.join(os.path.dirname(__file__), 'files')
+    model_dir = os.path.join(os.path.dirname(__file__), 'src', 'silero_vad', 'data')
     if onnx:
         model = OnnxWrapper(os.path.join(model_dir, 'silero_vad.onnx'), force_onnx_cpu)
     else:

pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+[project]
+name = "silero-vad"
+version = "5.1"
+authors = [
+  {name="Silero Team", email="[email protected]"},
+]
+description = "Voice Activity Detector (VAD) by Silero"
+readme = "README.md"
+requires-python = ">=3.8"
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "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",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering",
+]
+dependencies = [
+  "torch>=1.12.0",
+  "torchaudio>=0.12.0",
+  "onnxruntime>=1.18.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/snakers4/silero-vad"
+Issues = "https://github.com/snakers4/silero-vad/issues"

silero-vad.ipynb

@@ -43,20 +43,30 @@
    },
    "outputs": [],
    "source": [
+    "USE_PIP = True # download model using pip package or torch.hub\n",
     "USE_ONNX = False # change this to True if you want to test onnx model\n",
     "if USE_ONNX:\n",
     "    !pip install -q onnxruntime\n",
+    "if USE_PIP:\n",
+    "  !pip install -q silero-vad\n",
+    "  from silero_vad import (load_silero_vad,\n",
+    "                          read_audio,\n",
+    "                          get_speech_timestamps,\n",
+    "                          save_audio,\n",
+    "                          VADIterator,\n",
+    "                          collect_chunks)\n",
+    "  model = load_silero_vad(onnx=USE_ONNX)\n",
+    "else:\n",
+    "  model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',\n",
+    "                                model='silero_vad',\n",
+    "                                force_reload=True,\n",
+    "                                onnx=USE_ONNX)\n",
     "\n",
-    "model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',\n",
-    "                              model='silero_vad',\n",
-    "                              force_reload=True,\n",
-    "                              onnx=USE_ONNX)\n",
-    "\n",
-    "(get_speech_timestamps,\n",
-    " save_audio,\n",
-    " read_audio,\n",
-    " VADIterator,\n",
-    " collect_chunks) = utils"
+    "  (get_speech_timestamps,\n",
+    "  save_audio,\n",
+    "  read_audio,\n",
+    "  VADIterator,\n",
+    "  collect_chunks) = utils"
    ]
   },
   {

src/silero_vad/__init__.py

@@ -0,0 +1,12 @@
+from importlib.metadata import version
+try:
+    __version__ = version(__name__)
+except:
+    pass
+
+from silero_vad.model import load_silero_vad
+from silero_vad.utils_vad import (get_speech_timestamps,
+                                  save_audio,
+                                  read_audio,
+                                  VADIterator,
+                                  collect_chunks)

src/silero_vad/model.py

@@ -0,0 +1,25 @@
+from .utils_vad import init_jit_model, OnnxWrapper
+import torch
+torch.set_num_threads(1)
+
+def load_silero_vad(onnx=False):
+    model_name = 'silero_vad.onnx' if onnx else 'silero_vad.jit'
+    package_path = "silero_vad.data"
+
+    try:
+        import importlib_resources as impresources
+        model_file_path = str(impresources.files(package_path).joinpath(model_name))
+    except:
+        from importlib import resources as impresources
+        try:
+            with impresources.path(package_path, model_name) as f:
+                model_file_path = f
+        except:
+            model_file_path = str(impresources.files(package_path).joinpath(model_name))
+
+    if onnx:
+        model = OnnxWrapper(model_file_path, force_onnx_cpu=True)
+    else:
+        model = init_jit_model(model_file_path)
+
+    return model

utils_vad.py → src/silero_vad/utils_vad.py

@@ -132,18 +132,19 @@ def __call__(self, inputs: torch.Tensor):
 
 def read_audio(path: str,
                sampling_rate: int = 16000):
+    list_backends = torchaudio.list_audio_backends()
+
+    assert len(list_backends) > 0, 'The list of available backends is empty, please install backend manually. \
+                                    \n Recommendations: \n \tSox (UNIX OS) \n \tSoundfile (Windows OS, UNIX OS) \n \tffmpeg (Windows OS, UNIX OS)'
 
-    sox_backends = set(['sox', 'sox_io'])
-    audio_backends = torchaudio.list_audio_backends()
-
-    if len(sox_backends.intersection(audio_backends)) > 0:
+    try:
         effects = [
             ['channels', '1'],
             ['rate', str(sampling_rate)]
         ]
 
         wav, sr = torchaudio.sox_effects.apply_effects_file(path, effects=effects)
-    else:
+    except:
         wav, sr = torchaudio.load(path)
 
         if wav.size(0) > 1: