Spaces:
Paused
Paused
File size: 9,024 Bytes
ee6e328 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"%matplotlib inline\n",
"\n",
"from TTS.utils.audio import AudioProcessor\n",
"from TTS.tts.utils.visual import plot_spectrogram\n",
"from TTS.config import load_config\n",
"\n",
"import IPython.display as ipd\n",
"import glob"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"from TTS.config.shared_configs import BaseAudioConfig\n",
"CONFIG = BaseAudioConfig()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ✍️ Set these values "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"data_path = \"/root/wav48_silence_trimmed/\"\n",
"file_ext = \".flac\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Read audio files"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"file_paths = glob.glob(data_path + f\"/**/*{file_ext}\", recursive=True)\n",
"\n",
"# Change this to the index of the desired file listed below\n",
"sample_file_index = 10\n",
"\n",
"SAMPLE_FILE_PATH = file_paths[sample_file_index]\n",
"\n",
"print(\"File list, by index:\")\n",
"dict(enumerate(file_paths))"
]
},
{
"cell_type": "markdown",
"metadata": {
"Collapsed": "false"
},
"source": [
"## ✍️ Set Audio Processor\n",
"Play with the AP parameters until you find a good fit with the synthesis speech below.\n",
"\n",
"The default values are loaded from your config.json file, so you only need to\n",
"uncomment and modify values below that you'd like to tune."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"tune_params={\n",
" 'num_mels': 80, # In general, you don't need to change this. \n",
" 'fft_size': 2400, # In general, you don't need to change this.\n",
" 'frame_length_ms': 50, \n",
" 'frame_shift_ms': 12.5,\n",
" 'sample_rate': 48000, # This must match the sample rate of the dataset.\n",
" 'hop_length': None, # In general, you don't need to change this.\n",
" 'win_length': 1024, # In general, you don't need to change this.\n",
" 'preemphasis': 0.98, # In general, 0 gives better voice recovery but makes training harder. If your model does not train, try 0.97 - 0.99.\n",
" 'min_level_db': -100,\n",
" 'ref_level_db': 0, # The base DB; increase until all background noise is removed in the spectrogram, then lower until you hear better speech below.\n",
" 'power': 1.5, # Change this value and listen to the synthesized voice. 1.2 - 1.5 are resonable values.\n",
" 'griffin_lim_iters': 60, # Quality does not improve for values > 60\n",
" 'mel_fmin': 0.0, # Adjust this and check mel-spectrogram-based voice synthesis below.\n",
" 'mel_fmax': 8000.0, # Adjust this and check mel-spectrogram-based voice synthesis below.\n",
" 'do_trim_silence': True # If you dataset has some silience at the beginning or end, this trims it. Check the AP.load_wav() below,if it causes any difference for the loaded audio file.\n",
"}\n",
"\n",
"# These options have to be forced off in order to avoid errors about the \n",
"# pre-calculated not matching the options being tuned.\n",
"reset={\n",
" 'signal_norm': True, # check this if you want to test normalization parameters.\n",
" 'stats_path': None,\n",
" 'symmetric_norm': False,\n",
" 'max_norm': 1,\n",
" 'clip_norm': True,\n",
"}\n",
"\n",
"# Override select parts of loaded config with parameters above\n",
"tuned_config = CONFIG.copy()\n",
"tuned_config.update(reset)\n",
"tuned_config.update(tune_params)\n",
"\n",
"AP = AudioProcessor(**tuned_config);"
]
},
{
"cell_type": "markdown",
"metadata": {
"Collapsed": "false"
},
"source": [
"### Check audio loading "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"wav = AP.load_wav(SAMPLE_FILE_PATH)\n",
"ipd.Audio(data=wav, rate=AP.sample_rate) "
]
},
{
"cell_type": "markdown",
"metadata": {
"Collapsed": "false"
},
"source": [
"### Generate Mel-Spectrogram and Re-synthesis with GL"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"AP.power = 1.5"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"mel = AP.melspectrogram(wav)\n",
"print(\"Max:\", mel.max())\n",
"print(\"Min:\", mel.min())\n",
"print(\"Mean:\", mel.mean())\n",
"plot_spectrogram(mel.T, AP, output_fig=True)\n",
"\n",
"wav_gen = AP.inv_melspectrogram(mel)\n",
"ipd.Audio(wav_gen, rate=AP.sample_rate)"
]
},
{
"cell_type": "markdown",
"metadata": {
"Collapsed": "false"
},
"source": [
"### Generate Linear-Spectrogram and Re-synthesis with GL"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"spec = AP.spectrogram(wav)\n",
"print(\"Max:\", spec.max())\n",
"print(\"Min:\", spec.min())\n",
"print(\"Mean:\", spec.mean())\n",
"plot_spectrogram(spec.T, AP, output_fig=True)\n",
"\n",
"wav_gen = AP.inv_spectrogram(spec)\n",
"ipd.Audio(wav_gen, rate=AP.sample_rate)"
]
},
{
"cell_type": "markdown",
"metadata": {
"Collapsed": "false"
},
"source": [
"### Compare values for a certain parameter\n",
"\n",
"Optimize your parameters by comparing different values per parameter at a time."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"from librosa import display\n",
"from matplotlib import pylab as plt\n",
"import IPython\n",
"plt.rcParams['figure.figsize'] = (20.0, 16.0)\n",
"\n",
"def compare_values(attribute, values):\n",
" \"\"\"\n",
" attributes (str): the names of the attribute you like to test.\n",
" values (list): list of values to compare.\n",
" \"\"\"\n",
" file = SAMPLE_FILE_PATH\n",
" wavs = []\n",
" for idx, val in enumerate(values):\n",
" set_val_cmd = \"AP.{}={}\".format(attribute, val)\n",
" exec(set_val_cmd)\n",
" wav = AP.load_wav(file)\n",
" spec = AP.spectrogram(wav)\n",
" spec_norm = AP.denormalize(spec.T)\n",
" plt.subplot(len(values), 2, 2*idx + 1)\n",
" plt.imshow(spec_norm.T, aspect=\"auto\", origin=\"lower\")\n",
" # plt.colorbar()\n",
" plt.tight_layout()\n",
" wav_gen = AP.inv_spectrogram(spec)\n",
" wavs.append(wav_gen)\n",
" plt.subplot(len(values), 2, 2*idx + 2)\n",
" display.waveplot(wav, alpha=0.5)\n",
" display.waveplot(wav_gen, alpha=0.25)\n",
" plt.title(\"{}={}\".format(attribute, val))\n",
" plt.tight_layout()\n",
" \n",
" wav = AP.load_wav(file)\n",
" print(\" > Ground-truth\")\n",
" IPython.display.display(IPython.display.Audio(wav, rate=AP.sample_rate))\n",
" \n",
" for idx, wav_gen in enumerate(wavs):\n",
" val = values[idx]\n",
" print(\" > {} = {}\".format(attribute, val))\n",
" IPython.display.display(IPython.display.Audio(wav_gen, rate=AP.sample_rate))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"compare_values(\"preemphasis\", [0, 0.5, 0.97, 0.98, 0.99])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"compare_values(\"ref_level_db\", [2, 5, 10, 15, 20, 25, 30, 35, 40, 1000])"
]
}
],
"metadata": {
"interpreter": {
"hash": "27648abe09795c3a768a281b31f7524fcf66a207e733f8ecda3a4e1fd1059fb0"
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|