File size: 6,025 Bytes
9642163 aa88eb2 9642163 aa88eb2 9642163 aa88eb2 9642163 aa88eb2 9642163 aa88eb2 9642163 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# DAC Audio Tokenizer"
]
},
{
"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": [
"import os\n",
"from pathlib import Path\n",
"\n",
"from model import DAC, DACConfig"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# settings\n",
"fname = str(Path(os.getcwd()).joinpath('.sample_sound', 'jazz_swing.wav'))\n",
"device = 'cpu'\n",
"model_type_by_sampling_freq = '16khz'"
]
},
{
"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": [
"# load the model\n",
"config = DACConfig(model_type_by_sampling_freq=model_type_by_sampling_freq)\n",
"model = DAC(config).to(device)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"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": [
"# encoding\n",
"zq, s = model.encode(fname)\n",
"print('zq.shape:', zq.shape)\n",
"print('s.shape:', s.shape)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"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": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"waveform.shape: torch.Size([1, 1, 159912])\n"
]
}
],
"source": [
"# decoding (from s -- tokens)\n",
"waveform = model.decode(s=s)\n",
"print('waveform.shape:', waveform.shape)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"# save waveform into an audio file\n",
"model.waveform_to_audiofile(waveform, 'out.wav')"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"d:\\projects\\descript-audio-codec-16khz\\model.py:213: 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",
" return torch.load(fname)\n"
]
}
],
"source": [
"# save and load tokens\n",
"model.save_tensor(s, 'tokens.pt')\n",
"loaded_s = model.load_tensor('tokens.pt') # s == loaded_s"
]
},
{
"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
}
|