{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "\n# Audio Datasets\n\n**Author**: [Moto Hira](moto@meta.com)_\n\n``torchaudio`` provides easy access to common, publicly accessible\ndatasets. Please refer to the official documentation for the list of\navailable datasets.\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "import torch\nimport torchaudio\n\nprint(torch.__version__)\nprint(torchaudio.__version__)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "import os\n\nimport IPython\n\nimport matplotlib.pyplot as plt\n\n\n_SAMPLE_DIR = \"_assets\"\nYESNO_DATASET_PATH = os.path.join(_SAMPLE_DIR, \"yes_no\")\nos.makedirs(YESNO_DATASET_PATH, exist_ok=True)\n\n\ndef plot_specgram(waveform, sample_rate, title=\"Spectrogram\"):\n waveform = waveform.numpy()\n\n figure, ax = plt.subplots()\n ax.specgram(waveform[0], Fs=sample_rate)\n figure.suptitle(title)\n figure.tight_layout()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Here, we show how to use the\n:py:class:`torchaudio.datasets.YESNO` dataset.\n\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "dataset = torchaudio.datasets.YESNO(YESNO_DATASET_PATH, download=True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "i = 1\nwaveform, sample_rate, label = dataset[i]\nplot_specgram(waveform, sample_rate, title=f\"Sample {i}: {label}\")\nIPython.display.Audio(waveform, rate=sample_rate)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "i = 3\nwaveform, sample_rate, label = dataset[i]\nplot_specgram(waveform, sample_rate, title=f\"Sample {i}: {label}\")\nIPython.display.Audio(waveform, rate=sample_rate)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "i = 5\nwaveform, sample_rate, label = dataset[i]\nplot_specgram(waveform, sample_rate, title=f\"Sample {i}: {label}\")\nIPython.display.Audio(waveform, rate=sample_rate)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.14" } }, "nbformat": 4, "nbformat_minor": 0 }