diff --git "a/example.ipynb" "b/example.ipynb" new file mode 100644--- /dev/null +++ "b/example.ipynb" @@ -0,0 +1,171 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Kokoro-82M ONNX Runtime Inference" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# Import required libraries\n", + "import numpy as np\n", + "from IPython.display import display, Audio\n", + "\n", + "# Import the Kokoro model class\n", + "from models import Tokenizer, Kokoro" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "model_path = \"weights/kokoro-v0_19.onnx\"\n", + "output_filename = \"output.wav\"\n", + "style_vector_path = \"voices/af_bella.pt\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Initialize Tokenizer and Kokoro model" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "tokenizer = Tokenizer()\n", + "\n", + "kokoro = Kokoro(model_path, style_vector_path, tokenizer=tokenizer, lang='en-us')\n" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "text = (\n", + " \"This approach ensures the entire text is processed without exceeding the token limit and outputs seamless audio for the full input. \"\n", + " \"Let me know if you need further assistance!\"\n", + ")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Generate audio" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "audio, sample_rate = kokoro.generate_audio(text, speed=1.0)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Display the output on jupyter" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display(Audio(data=audio, rate=24000, autoplay=True))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Save model the output" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Audio saved to output.wav\n" + ] + } + ], + "source": [ + "import soundfile as sf\n", + "\n", + "sf.write(output_filename, audio, sample_rate)\n", + "print(f\"Audio saved to {output_filename}\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "torch", + "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": 2 +}