{
"cells": [
{
"cell_type": "markdown",
"id": "0fd939b0",
"metadata": {},
"source": [
"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "6c7800a6",
"metadata": {},
"outputs": [],
"source": [
"try:\n",
" # are we running on Google Colab?\n",
" import google.colab\n",
" !git clone -q https://github.com/teticio/audio-diffusion.git\n",
" %cd audio-diffusion\n",
" !pip install -q -r requirements.txt\n",
"except:\n",
" pass"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "b447e2c4",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"sys.path.insert(0, os.path.dirname(os.path.abspath(\"\")))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "c2fc0e7a",
"metadata": {},
"outputs": [],
"source": [
"import random\n",
"from PIL import Image\n",
"from src.mel import Mel\n",
"from IPython.display import Audio\n",
"from datasets import load_dataset\n",
"from diffusers import DDPMPipeline"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a3d45c36",
"metadata": {},
"outputs": [],
"source": [
"mel = Mel(x_res=256, y_res=256)"
]
},
{
"cell_type": "markdown",
"id": "011fb5a1",
"metadata": {},
"source": [
"### Run model inference to generate mel spectrogram"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "b809fed5",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "51af6bb05a1b4993b1ef37924ffa0e28",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/1000 [00:00"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"image = Image.fromarray(images[0][0])\n",
"image"
]
},
{
"cell_type": "markdown",
"id": "7230c280",
"metadata": {},
"source": [
"### Transform mel spectrogram to audio"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "5f8a149d",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"audio = mel.image_to_audio(image)\n",
"Audio(data=audio, rate=mel.get_sample_rate())"
]
},
{
"cell_type": "markdown",
"id": "ef54cef3",
"metadata": {},
"source": [
"### Compare results with random sample from training set"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "269ee816",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using custom data configuration teticio--audio-difussion-data-256-67e42008226ba2a6\n",
"Reusing dataset parquet (/home/teticio/.cache/huggingface/datasets/teticio___parquet/teticio--audio-difussion-data-256-67e42008226ba2a6/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9f9e310b378f4b7680736fea1de56773",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/1 [00:00"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"image = random.choice(ds['train'])['image']\n",
"image"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "492e2334",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"audio = mel.image_to_audio(image)\n",
"Audio(data=audio, rate=mel.get_sample_rate())"
]
},
{
"cell_type": "markdown",
"id": "946fdb4d",
"metadata": {},
"source": [
"### Push model to hub"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "37c0564e",
"metadata": {},
"outputs": [],
"source": [
"from diffusers.hub_utils import init_git_repo, push_to_hub\n",
"\n",
"\n",
"class AttributeDict(dict):\n",
"\n",
" def __getattr__(self, attr):\n",
" return self[attr]\n",
"\n",
" def __setattr__(self, attr, value):\n",
" self[attr] = value\n",
"\n",
"\n",
"args = AttributeDict({\n",
" \"hub_model_id\":\n",
" \"teticio/audio-diffusion-256\",\n",
" \"output_dir\":\n",
" \"../ddpm-ema-audio-256-repo\",\n",
" \"local_rank\":\n",
" -1,\n",
" \"hub_token\":\n",
" open(os.path.join(os.environ['HOME'], '.huggingface/token'), 'rt').read(),\n",
" \"hub_private_repo\":\n",
" False,\n",
" \"overwrite_output_dir\":\n",
" False\n",
"})\n",
"\n",
"repo = init_git_repo(args, at_init=True)\n",
"ddpm = DDPMPipeline.from_pretrained('../ddpm-ema-audio-256')\n",
"push_to_hub(args, ddpm, repo)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8c8261a0",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "huggingface",
"language": "python",
"name": "huggingface"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": false,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {},
"toc_section_display": true,
"toc_window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 5
}