diff --git "a/external_models/TangoFlux/Inference.ipynb" "b/external_models/TangoFlux/Inference.ipynb" new file mode 100644--- /dev/null +++ "b/external_models/TangoFlux/Inference.ipynb" @@ -0,0 +1,79 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Fetching 5 files: 100%|██████████| 5/5 [00:00<00:00, 76818.75it/s]\n", + " 0%| | 0/50 [01:05\n", + " \n", + " Your browser does not support the audio element.\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import torchaudio\n", + "from tangoflux import TangoFluxInference\n", + "from IPython.display import Audio\n", + "\n", + "model = TangoFluxInference(name=\"declare-lab/TangoFlux\")\n", + "\n", + "\n", + "audio = model.generate(\"Hammer slowly hitting the wooden table\", steps=50, duration=10)\n", + "\n", + "Audio(data=audio, rate=44100)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [], + "source": [ + "torchaudio.save(\"temp.wav\", audio, sample_rate=44100)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "flux", + "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": "3.12.8" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}