diff --git "a/notebooks/CLI_Example.ipynb" "b/notebooks/CLI_Example.ipynb"
new file mode 100644--- /dev/null
+++ "b/notebooks/CLI_Example.ipynb"
@@ -0,0 +1,254 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": [],
+ "gpuType": "T4",
+ "include_colab_link": true
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ },
+ "accelerator": "GPU"
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "view-in-github",
+ "colab_type": "text"
+ },
+ "source": [
+ ""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Install"
+ ],
+ "metadata": {
+ "id": "UsW1zD1cRqoX"
+ }
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "_F_3LjI8zYiw",
+ "outputId": "d8930d99-0d4a-4f7c-cbda-9774057672a2"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Cloning into 'deep-voice-cloning'...\n",
+ "remote: Enumerating objects: 27, done.\u001b[K\n",
+ "remote: Counting objects: 100% (27/27), done.\u001b[K\n",
+ "remote: Compressing objects: 100% (24/24), done.\u001b[K\n",
+ "remote: Total 27 (delta 0), reused 27 (delta 0), pack-reused 0\u001b[K\n",
+ "Receiving objects: 100% (27/27), 1.36 MiB | 29.07 MiB/s, done.\n"
+ ]
+ }
+ ],
+ "source": [
+ "!git clone https://github.com/konverner/deep-voice-cloning.git"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "%cd deep-voice-cloning\n",
+ "!pip install . > null"
+ ],
+ "metadata": {
+ "id": "YctLbHO10ou9",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "5940018d-67bd-4d8d-ce84-0c7a5b92ff44"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "/content/deep-voice-cloning/deep-voice-cloning\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Cloning Voice of Hank Hill"
+ ],
+ "metadata": {
+ "id": "caTAhpANGlnL"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!python scripts/train.py --audio_path \"/content/deep-voice-cloning/scripts/input/hank.mp3\"\\\n",
+ " --output_dir \"/content/deep-voice-cloning/models\""
+ ],
+ "metadata": {
+ "id": "lYz6IM4ZGlSa"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!python scripts/cloning_inference.py --model_path \"/content/deep-voice-cloning/models/microsoft_speecht5_tts_hank\"\\\n",
+ " --input_text 'do the things, not because they are easy, but because they are hard'\\\n",
+ " --output_path \"scripts/output/do_the_things.wav\""
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "_AFvKCrqOPsk",
+ "outputId": "5f1b096c-04e5-4645-d13e-3878ef12a8f3"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "2023-07-22 11:29:53.541592: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from IPython import display\n",
+ "display.Audio(\"/content/deep-voice-cloning/scripts/output/do_the_things.wav\")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 75
+ },
+ "id": "QmboXL9LOSKD",
+ "outputId": "f682399c-7111-4957-cc05-c854f9ab7d19"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " "
+ ]
+ },
+ "metadata": {},
+ "execution_count": 14
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Cloning Voice of Homer Simpson"
+ ],
+ "metadata": {
+ "id": "hNlD1Ocfjp1k"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!python scripts/train.py --audio_path \"/content/deep-voice-cloning/scripts/input/homer.mp3\"\\\n",
+ " --output_dir \"/content/deep-voice-cloning/models\""
+ ],
+ "metadata": {
+ "id": "p15KMsOT0vKY"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!python scripts/cloning_inference.py --input_text 'do the things, not because they are easy, but because they are hard' --output_path \"scripts/output/do_the_things.wav\""
+ ],
+ "metadata": {
+ "id": "UHUi1maPI6jJ",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "45fefc02-4551-46fc-cc2e-2e43b589aa80"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "2023-07-21 22:24:34.290393: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from IPython import display\n",
+ "display.Audio(\"/content/deep-voice-cloning/scripts/output/do_the_things.wav\")"
+ ],
+ "metadata": {
+ "id": "Gl7sjDiKS4eI",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 75
+ },
+ "outputId": "c9d1b9af-9a1d-472b-804f-e17011d52135"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " "
+ ]
+ },
+ "metadata": {},
+ "execution_count": 16
+ }
+ ]
+ }
+ ]
+}
\ No newline at end of file