diff --git a/examples/pyaudio-streaming/README.md b/examples/pyaudio-streaming/README.md index 33e4760..c83bb78 100644 --- a/examples/pyaudio-streaming/README.md +++ b/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 diff --git a/examples/pyaudio-streaming/pyaudio-streaming-examples.ipynb b/examples/pyaudio-streaming/pyaudio-streaming-examples.ipynb index 94c8240..4a577d4 100644 --- a/examples/pyaudio-streaming/pyaudio-streaming-examples.ipynb +++ b/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,