Spaces:
Paused
Paused
File size: 10,050 Bytes
45ee559 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"# TTS_PATH = \"/home/erogol/projects/\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"import librosa\n",
"import numpy as np\n",
"import pandas as pd\n",
"from scipy.stats import norm\n",
"from tqdm import tqdm_notebook as tqdm\n",
"from multiprocessing import Pool\n",
"from matplotlib import pylab as plt\n",
"from collections import Counter\n",
"from TTS.config.shared_configs import BaseDatasetConfig\n",
"from TTS.tts.datasets import load_tts_samples\n",
"from TTS.tts.datasets.formatters import *\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"NUM_PROC = 8\n",
"DATASET_CONFIG = BaseDatasetConfig(\n",
" formatter=\"ljspeech\", meta_file_train=\"metadata.csv\", path=\"/absolute/path/to/your/dataset/\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def formatter(root_path, meta_file, **kwargs): # pylint: disable=unused-argument\n",
" txt_file = os.path.join(root_path, meta_file)\n",
" items = []\n",
" speaker_name = \"myspeaker\"\n",
" with open(txt_file, \"r\", encoding=\"utf-8\") as ttf:\n",
" for line in ttf:\n",
" cols = line.split(\"|\")\n",
" wav_file = os.path.join(root_path, \"wavs\", cols[0] + \".wav\") \n",
" text = cols[1]\n",
" items.append({\"text\": text, \"audio_file\": wav_file, \"speaker_name\": speaker_name, \"root_path\": root_path})\n",
" return items"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"# use your own preprocessor at this stage - TTS/datasets/proprocess.py\n",
"train_samples, eval_samples = load_tts_samples(DATASET_CONFIG, eval_split=True, formatter=formatter)\n",
"if eval_samples is not None:\n",
" items = train_samples + eval_samples\n",
"else:\n",
" items = train_samples\n",
"print(\" > Number of audio files: {}\".format(len(items)))\n",
"print(items[1])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"# check wavs if exist\n",
"wav_files = []\n",
"for item in items:\n",
" wav_file = item[\"audio_file\"].strip()\n",
" wav_files.append(wav_file)\n",
" if not os.path.exists(wav_file):\n",
" print(waf_path)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"# show duplicate items\n",
"c = Counter(wav_files)\n",
"print([item for item, count in c.items() if count > 1])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"item"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"def load_item(item):\n",
" text = item[\"text\"].strip()\n",
" file_name = item[\"audio_file\"].strip()\n",
" audio, sr = librosa.load(file_name, sr=None)\n",
" audio_len = len(audio) / sr\n",
" text_len = len(text)\n",
" return file_name, text, text_len, audio, audio_len\n",
"\n",
"# This will take a while depending on size of dataset\n",
"if NUM_PROC == 1:\n",
" data = []\n",
" for m in tqdm(items):\n",
" data += [load_item(m)]\n",
"else:\n",
" with Pool(8) as p:\n",
" data = list(tqdm(p.imap(load_item, items), total=len(items)))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"# count words in the dataset\n",
"w_count = Counter()\n",
"for item in tqdm(data):\n",
" text = item[1].lower().strip()\n",
" for word in text.split():\n",
" w_count[word] += 1\n",
"print(\" > Number of words: {}\".format(len(w_count)))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"text_vs_durs = {} # text length vs audio duration\n",
"text_len_counter = Counter() # number of sentences with the keyed length\n",
"for item in tqdm(data):\n",
" text = item[1].lower().strip()\n",
" text_len = len(text)\n",
" text_len_counter[text_len] += 1\n",
" audio_len = item[-1]\n",
" try:\n",
" text_vs_durs[text_len] += [audio_len]\n",
" except:\n",
" text_vs_durs[text_len] = [audio_len]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"# text_len vs avg_audio_len, median_audio_len, std_audio_len\n",
"text_vs_avg = {}\n",
"text_vs_median = {}\n",
"text_vs_std = {}\n",
"for key, durs in text_vs_durs.items():\n",
" text_vs_avg[key] = np.mean(durs)\n",
" text_vs_median[key] = np.median(durs)\n",
" text_vs_std[key] = np.std(durs)"
]
},
{
"cell_type": "markdown",
"metadata": {
"Collapsed": "false"
},
"source": [
"### Avg audio length per char"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"for item in data:\n",
" if item[-1] < 2:\n",
" print(item)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"sec_per_chars = []\n",
"for item in data:\n",
" text = item[1]\n",
" dur = item[-1]\n",
" sec_per_char = dur / len(text)\n",
" sec_per_chars.append(sec_per_char)\n",
"# sec_per_char /= len(data)\n",
"# print(sec_per_char)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"mean = np.mean(sec_per_chars)\n",
"std = np.std(sec_per_chars)\n",
"print(mean)\n",
"print(std)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"dist = norm(mean, std)\n",
"\n",
"# find irregular instances long or short voice durations\n",
"for item in data:\n",
" text = item[1]\n",
" dur = item[-1]\n",
" sec_per_char = dur / len(text)\n",
" pdf =norm.pdf(sec_per_char)\n",
" if pdf < 0.39:\n",
" print(item)"
]
},
{
"cell_type": "markdown",
"metadata": {
"Collapsed": "false"
},
"source": [
"### Plot Dataset Statistics"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"plt.title(\"text length vs mean audio duration\")\n",
"plt.scatter(list(text_vs_avg.keys()), list(text_vs_avg.values()))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"plt.title(\"text length vs median audio duration\")\n",
"plt.scatter(list(text_vs_median.keys()), list(text_vs_median.values()))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"plt.title(\"text length vs STD\")\n",
"plt.scatter(list(text_vs_std.keys()), list(text_vs_std.values()))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"plt.title(\"text length vs # instances\")\n",
"plt.scatter(list(text_len_counter.keys()), list(text_len_counter.values()))"
]
},
{
"cell_type": "markdown",
"metadata": {
"Collapsed": "false"
},
"source": [
"### Check words frequencies"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"w_count_df = pd.DataFrame.from_dict(w_count, orient='index')\n",
"w_count_df.sort_values(0, ascending=False, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false",
"scrolled": true
},
"outputs": [],
"source": [
"w_count_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"# check a certain word\n",
"w_count_df.at['minute', 0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
"outputs": [],
"source": [
"# fequency bar plot - it takes time!!\n",
"w_count_df.plot.bar()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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": "3.9.12"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|