{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\dslee\\AppData\\Roaming\\Python\\Python38\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from model import DACConfig, DAC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Registering a model with custom code to the auto classes\n",
    "DACConfig.register_for_auto_class()\n",
    "DAC.register_for_auto_class()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\dslee\\AppData\\Roaming\\Python\\Python38\\site-packages\\audiotools\\ml\\layers\\base.py:172: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
      "  model_dict = torch.load(location, \"cpu\")\n",
      "c:\\Users\\dslee\\anaconda3\\envs\\sound_effect_variation_generation\\lib\\site-packages\\torch\\nn\\utils\\weight_norm.py:134: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.\n",
      "  WeightNorm.apply(module, name, dim)\n"
     ]
    }
   ],
   "source": [
    "# create instances\n",
    "config = DACConfig(model_type_by_sampling_freq='16khz')\n",
    "model = DAC(config)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\dslee\\anaconda3\\envs\\sound_effect_variation_generation\\lib\\site-packages\\huggingface_hub\\file_download.py:159: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\dslee\\.cache\\huggingface\\hub\\models--hance-ai--descript-audio-codec-16khz. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
      "  warnings.warn(message)\n",
      "model.safetensors: 100%|██████████| 297M/297M [00:11<00:00, 26.9MB/s] \n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "CommitInfo(commit_url='https://huggingface.co/hance-ai/descript-audio-codec-16khz/commit/67523817a195ced323d12ce4c439590547d8e9c7', commit_message='Upload DAC', commit_description='', oid='67523817a195ced323d12ce4c439590547d8e9c7', pr_url=None, pr_revision=None, pr_num=None)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# push the model to the huggingface\n",
    "with open('token.txt', 'r') as file:\n",
    "    token = file.read().strip()\n",
    "\n",
    "model.push_to_hub('hance-ai/descript-audio-codec-16khz', token=token)  # put your token"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Recommend git fetching and pulling so that the uploaded model is synced locally too."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "***"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\dslee\\AppData\\Roaming\\Python\\Python38\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n",
      "c:\\Users\\dslee\\anaconda3\\envs\\sound_effect_variation_generation\\lib\\site-packages\\huggingface_hub\\file_download.py:159: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\dslee\\.cache\\huggingface\\hub\\models--hance-ai--descript-audio-codec-16khz. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
      "  warnings.warn(message)\n",
      "A new version of the following files was downloaded from https://huggingface.co/hance-ai/descript-audio-codec-16khz:\n",
      "- model.py\n",
      ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",
      "C:\\Users\\dslee\\AppData\\Roaming\\Python\\Python38\\site-packages\\audiotools\\ml\\layers\\base.py:172: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
      "  model_dict = torch.load(location, \"cpu\")\n",
      "c:\\Users\\dslee\\anaconda3\\envs\\sound_effect_variation_generation\\lib\\site-packages\\torch\\nn\\utils\\weight_norm.py:134: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.\n",
      "  WeightNorm.apply(module, name, dim)\n"
     ]
    }
   ],
   "source": [
    "# load the uploaded model\n",
    "from transformers import AutoModel\n",
    "model = AutoModel.from_pretrained('hance-ai/descript-audio-codec-16khz', trust_remote_code=True)\n",
    "model.to('cpu');"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "zq.shape: torch.Size([1, 1024, 500])\n",
      "s.shape: torch.Size([1, 12, 500])\n"
     ]
    }
   ],
   "source": [
    "# encodeing\n",
    "import os\n",
    "from pathlib import Path\n",
    "\n",
    "fname = str(Path(os.getcwd()).joinpath('.sample_sound', 'jazz_swing.wav'))\n",
    "zq, s = model.encode(fname)\n",
    "print('zq.shape:', zq.shape)\n",
    "print('s.shape:', s.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "waveform.shape: torch.Size([1, 1, 159912])\n"
     ]
    }
   ],
   "source": [
    "# decoding (from zq -- discrete latent vectors)\n",
    "waveform = model.decode(zq=zq)\n",
    "print('waveform.shape:', waveform.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "sound_effect_variation_generation",
   "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": "3.8.19"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}