Update pyproject.toml

Adamnsandle

README.md

@@ -32,21 +32,28 @@ https://user-images.githubusercontent.com/36505480/144874384-95f80f6d-a4f1-42cc-
 <details>
 <summary>Dependencies</summary>
 
-  System requirements to run python examples:
-  - `python 3.8+`
-  - 1G+ RAM
-  - not too outdated cpu
+  System requirements to run python examples on `x86-64` systems:
+  
+  - `python 3.8+`;
+  - 1G+ RAM;
+  - A modern CPU with AVX, AVX2, AVX-512 or AMX instruction sets.
 
   Dependencies:
-  - `torch>=1.12.0`
-  - `torchaudio>=0.12.0` (for I/O functionalities only)
-  - `onnxruntime>=1.16.1` (for ONNX model usage)
   
-  Silero VAD uses torchaudio library for audio file I/O functionalities, which are torchaudio.info, torchaudio.load, and torchaudio.save, so a proper audio backend is required:
+  - `torch>=1.12.0`;
+  - `torchaudio>=0.12.0` (for I/O only);
+  - `onnxruntime>=1.16.1` (for ONNX model usage).
   
-  - Option №1 - [**FFmpeg**](https://www.ffmpeg.org/) backend. `conda install -c conda-forge 'ffmpeg<7'`
-  - Option №2 - [**sox_io**](https://pypi.org/project/sox/) backend. `apt-get install sox`, TorchAudio is tested on libsox 14.4.2.
-  - Option №3 - [**soundfile**](https://pypi.org/project/soundfile/) backend. `pip install soundfile`
+  Silero VAD uses torchaudio library for audio I/O (`torchaudio.info`, `torchaudio.load`, and `torchaudio.save`), so a proper audio backend is required:
+  
+  - Option №1 - [**FFmpeg**](https://www.ffmpeg.org/) backend. `conda install -c conda-forge 'ffmpeg<7'`;
+  - Option №2 - [**sox_io**](https://pypi.org/project/sox/) backend. `apt-get install sox`, TorchAudio is tested on libsox 14.4.2;
+  - Option №3 - [**soundfile**](https://pypi.org/project/soundfile/) backend. `pip install soundfile`.
+
+If you are planning to run the VAD using solely the `onnx-runtime`, it will run on any other system architectures where onnx-runtume is [supported](https://onnxruntime.ai/getting-started). In this case please note that:
+
+- You will have to implement the I/O;
+- You will have to adapt the existing wrappers / examples / post-processing for your use-case.
 
 </details>
 

examples/colab_record_example.ipynb

@@ -17,6 +17,7 @@
    },
    "outputs": [],
    "source": [
+    "#!apt install ffmpeg\n",
     "!pip -q install pydub\n",
     "from google.colab import output\n",
     "from base64 import b64decode, b64encode\n",
@@ -37,13 +38,12 @@
     "                              model='silero_vad',\n",
     "                              force_reload=True)\n",
     "\n",
-    "def int2float(sound):\n",
-    "    abs_max = np.abs(sound).max()\n",
-    "    sound = sound.astype('float32')\n",
-    "    if abs_max > 0:\n",
-    "        sound *= 1/32768\n",
-    "    sound = sound.squeeze()\n",
-    "    return sound\n",
+    "def int2float(audio):\n",
+    "    samples = audio.get_array_of_samples()\n",
+    "    new_sound = audio._spawn(samples)\n",
+    "    arr = np.array(samples).astype(np.float32)\n",
+    "    arr = arr / np.abs(arr).max()\n",
+    "    return arr\n",
     "\n",
     "AUDIO_HTML = \"\"\"\n",
     "<script>\n",
@@ -68,10 +68,10 @@
     "    //bitsPerSecond: 8000, //chrome seems to ignore, always 48k\n",
     "    mimeType : 'audio/webm;codecs=opus'\n",
     "    //mimeType : 'audio/webm;codecs=pcm'\n",
-    "  };            \n",
+    "  };\n",
     "  //recorder = new MediaRecorder(stream, options);\n",
     "  recorder = new MediaRecorder(stream);\n",
-    "  recorder.ondataavailable = function(e) {            \n",
+    "  recorder.ondataavailable = function(e) {\n",
     "    var url = URL.createObjectURL(e.data);\n",
     "    // var preview = document.createElement('audio');\n",
     "    // preview.controls = true;\n",
@@ -79,7 +79,7 @@
     "    // document.body.appendChild(preview);\n",
     "\n",
     "    reader = new FileReader();\n",
-    "    reader.readAsDataURL(e.data); \n",
+    "    reader.readAsDataURL(e.data);\n",
     "    reader.onloadend = function() {\n",
     "      base64data = reader.result;\n",
     "      //console.log(\"Inside FileReader:\" + base64data);\n",
@@ -121,7 +121,7 @@
     "\n",
     "}\n",
     "});\n",
-    "      \n",
+    "\n",
     "</script>\n",
     "\"\"\"\n",
     "\n",
@@ -133,8 +133,8 @@
     "    audio.export('test.mp3', format='mp3')\n",
     "    audio = audio.set_channels(1)\n",
     "    audio = audio.set_frame_rate(16000)\n",
-    "    audio_float = int2float(np.array(audio.get_array_of_samples()))\n",
-    "    audio_tens = torch.tensor(audio_float )\n",
+    "    audio_float = int2float(audio)\n",
+    "    audio_tens = torch.tensor(audio_float)\n",
     "    return audio_tens\n",
     "\n",
     "def make_animation(probs, audio_duration, interval=40):\n",
@@ -154,19 +154,18 @@
     "    def animate(i):\n",
     "        x = i * interval / 1000 - 0.04\n",
     "        y = np.linspace(0, 1.02, 2)\n",
-    "        \n",
+    "\n",
     "        line.set_data(x, y)\n",
     "        line.set_color('#990000')\n",
     "        return line,\n",
+    "    anim = FuncAnimation(fig, animate, init_func=init, interval=interval, save_count=int(audio_duration / (interval / 1000)))\n",
     "\n",
-    "    anim = FuncAnimation(fig, animate, init_func=init, interval=interval, save_count=audio_duration / (interval / 1000))\n",
-    "\n",
-    "    f = r\"animation.mp4\" \n",
-    "    writervideo = FFMpegWriter(fps=1000/interval) \n",
+    "    f = r\"animation.mp4\"\n",
+    "    writervideo = FFMpegWriter(fps=1000/interval)\n",
     "    anim.save(f, writer=writervideo)\n",
     "    plt.close('all')\n",
     "\n",
-    "def combine_audio(vidname, audname, outname, fps=25): \n",
+    "def combine_audio(vidname, audname, outname, fps=25):\n",
     "    my_clip = mpe.VideoFileClip(vidname, verbose=False)\n",
     "    audio_background = mpe.AudioFileClip(audname)\n",
     "    final_clip = my_clip.set_audio(audio_background)\n",
@@ -174,15 +173,10 @@
     "\n",
     "def record_make_animation():\n",
     "  tensor = record()\n",
-    "\n",
     "  print('Calculating probabilities...')\n",
     "  speech_probs = []\n",
     "  window_size_samples = 512\n",
-    "  for i in range(0, len(tensor), window_size_samples):\n",
-    "      if len(tensor[i: i+ window_size_samples]) < window_size_samples:\n",
-    "        break\n",
-    "      speech_prob = model(tensor[i: i+ window_size_samples], 16000).item()\n",
-    "      speech_probs.append(speech_prob)\n",
+    "  speech_probs = model.audio_forward(tensor, sr=16000)[0].tolist()\n",
     "  model.reset_states()\n",
     "  print('Making animation...')\n",
     "  make_animation(speech_probs, len(tensor) / 16000)\n",
@@ -196,7 +190,9 @@
     "  <video width=800 controls>\n",
     "        <source src=\"%s\" type=\"video/mp4\">\n",
     "  </video>\n",
-    "  \"\"\" % data_url))"
+    "  \"\"\" % data_url))\n",
+    "\n",
+    "  return speech_probs"
    ]
   },
   {
@@ -216,7 +212,7 @@
    },
    "outputs": [],
    "source": [
-    "record_make_animation()"
+    "speech_probs = record_make_animation()"
    ]
   }
  ],

examples/parallel_example.ipynb

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -18,17 +17,19 @@
     "SAMPLING_RATE = 16000\n",
     "import torch\n",
     "from pprint import pprint\n",
+    "import time\n",
+    "import shutil\n",
     "\n",
     "torch.set_num_threads(1)\n",
     "NUM_PROCESS=4 # set to the number of CPU cores in the machine\n",
     "NUM_COPIES=8\n",
     "# download wav files, make multiple copies\n",
-    "for idx in range(NUM_COPIES):\n",
-    "    torch.hub.download_url_to_file('https://models.silero.ai/vad_models/en.wav', f\"en_example{idx}.wav\")\n"
+    "torch.hub.download_url_to_file('https://models.silero.ai/vad_models/en.wav', f\"en_example0.wav\")\n",
+    "for idx in range(NUM_COPIES-1):\n",
+    "    shutil.copy(f\"en_example0.wav\", f\"en_example{idx+1}.wav\")"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -54,7 +55,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -99,7 +99,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -127,7 +126,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "diarization",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -141,7 +140,20 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.15"
+   "version": "3.10.14"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
   }
  },
  "nbformat": 4,

examples/pyaudio-streaming/README.md

@@ -7,6 +7,8 @@ It has been designed as a low-level example for binary real-time streaming using
 Currently, the notebook consits of two examples:
  - One that records audio of a predefined length from the microphone, process it with Silero-VAD, and plots it afterwards.
  - The other one plots the speech probabilities in real-time (using jupyterplot) and records the audio until you press enter.
+ 
+ This example does not work in google colab! For local usage only.
 
 ## Example Video for the Real-Time Visualization
 

examples/pyaudio-streaming/pyaudio-streaming-examples.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "62a0cccb",
+   "id": "76aa55ba",
    "metadata": {},
    "source": [
     "# Pyaudio Microphone Streaming Examples\n",
@@ -12,12 +12,14 @@
     "I created it as an example on how binary data from a stream could be feed into Silero VAD.\n",
     "\n",
     "\n",
-    "Has been tested on Ubuntu 21.04 (x86). After you installed the dependencies below, no additional setup is required."
+    "Has been tested on Ubuntu 21.04 (x86). After you installed the dependencies below, no additional setup is required.\n",
+    "\n",
+    "This notebook does not work in google colab! For local usage only."
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "64cbe1eb",
+   "id": "4a4e15c2",
    "metadata": {},
    "source": [
     "## Dependencies\n",
@@ -26,22 +28,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "57bc2aac",
-   "metadata": {},
+   "execution_count": 1,
+   "id": "24205cce",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-10-09T08:47:34.056898Z",
+     "start_time": "2024-10-09T08:47:34.053418Z"
+    }
+   },
    "outputs": [],
    "source": [
-    "#!pip install numpy==2.0.2\n",
-    "#!pip install torch==2.4.1\n",
-    "#!pip install matplotlib==3.9.2\n",
-    "#!pip install torchaudio==2.4.1\n",
+    "#!pip install numpy>=1.24.0\n",
+    "#!pip install torch>=1.12.0\n",
+    "#!pip install matplotlib>=3.6.0\n",
+    "#!pip install torchaudio>=0.12.0\n",
     "#!pip install soundfile==0.12.1\n",
-    "#!pip install pyaudio==0.2.11"
+    "#!apt install python3-pyaudio (linux) or pip install pyaudio (windows)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "110de761",
+   "id": "cd22818f",
    "metadata": {},
    "source": [
     "## Imports"
@@ -49,10 +56,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "5a647d8d",
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 2,
+   "id": "994d7f3a",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-10-09T08:47:39.005032Z",
+     "start_time": "2024-10-09T08:47:36.489952Z"
+    }
+   },
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'pyaudio'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[2], line 8\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mmatplotlib\u001b[39;00m\n\u001b[1;32m      7\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mmatplotlib\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpylab\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mplt\u001b[39;00m\n\u001b[0;32m----> 8\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mpyaudio\u001b[39;00m\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'pyaudio'"
+     ]
+    }
+   ],
    "source": [
     "import io\n",
     "import numpy as np\n",
@@ -67,7 +91,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "725d7066",
+   "id": "ac5c52f7",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -79,7 +103,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1c0b2ea7",
+   "id": "ad5919dc",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -92,7 +116,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f9112603",
+   "id": "784d1ab6",
    "metadata": {},
    "source": [
     "### Helper Methods"
@@ -101,7 +125,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5abc6330",
+   "id": "af4bca64",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -124,7 +148,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5124095e",
+   "id": "ca13e514",
    "metadata": {},
    "source": [
     "## Pyaudio Set-up"
@@ -133,7 +157,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a845356e",
+   "id": "75f99022",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -147,7 +171,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0b910c99",
+   "id": "4da7d2ef",
    "metadata": {},
    "source": [
     "## Simple Example\n",
@@ -157,7 +181,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9d3d2c10",
+   "id": "6fe77661",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -167,7 +191,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3cb44a4a",
+   "id": "23f4da3e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -207,7 +231,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a3dda982",
+   "id": "fd243e8f",
    "metadata": {},
    "source": [
     "## Real Time Visualization\n",
@@ -220,7 +244,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "05ef4100",
+   "id": "d36980c2",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -230,7 +254,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d1d4cdd6",
+   "id": "5607b616",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -287,7 +311,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1e398009",
+   "id": "dc4f0108",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -311,7 +335,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.10"
+   "version": "3.10.14"
   },
   "toc": {
    "base_numbering": 1,

pyproject.toml

@@ -3,7 +3,7 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 [project]
 name = "silero-vad"
-version = "5.1"
+version = "5.1.2"
 authors = [
   {name="Silero Team", email="hello@silero.ai"},
 ]
@@ -32,4 +32,4 @@ dependencies = [
 
 [project.urls]
 Homepage = "https://github.com/snakers4/silero-vad"
-Issues = "https://github.com/snakers4/silero-vad/issues"
+Issues = "https://github.com/snakers4/silero-vad/issues"