Spaces:
Running
Running
File size: 15,496 Bytes
c24ff9a |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"./speakers_all.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"df['id'] = df['filename'].apply(lambda x: x + \".wav\")\n",
"df = df[df['file_missing?'] == False]"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>age_onset</th>\n",
" <th>birthplace</th>\n",
" <th>filename</th>\n",
" <th>native_language</th>\n",
" <th>sex</th>\n",
" <th>speakerid</th>\n",
" <th>country</th>\n",
" <th>file_missing?</th>\n",
" <th>Unnamed: 9</th>\n",
" <th>Unnamed: 10</th>\n",
" <th>Unnamed: 11</th>\n",
" <th>id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>27.0</td>\n",
" <td>9.0</td>\n",
" <td>virginia, south africa</td>\n",
" <td>afrikaans1</td>\n",
" <td>afrikaans</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>south africa</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>afrikaans1.wav</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>40.0</td>\n",
" <td>5.0</td>\n",
" <td>pretoria, south africa</td>\n",
" <td>afrikaans2</td>\n",
" <td>afrikaans</td>\n",
" <td>male</td>\n",
" <td>2</td>\n",
" <td>south africa</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>afrikaans2.wav</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>43.0</td>\n",
" <td>4.0</td>\n",
" <td>pretoria, transvaal, south africa</td>\n",
" <td>afrikaans3</td>\n",
" <td>afrikaans</td>\n",
" <td>male</td>\n",
" <td>418</td>\n",
" <td>south africa</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>afrikaans3.wav</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>26.0</td>\n",
" <td>8.0</td>\n",
" <td>pretoria, south africa</td>\n",
" <td>afrikaans4</td>\n",
" <td>afrikaans</td>\n",
" <td>male</td>\n",
" <td>1159</td>\n",
" <td>south africa</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>afrikaans4.wav</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>19.0</td>\n",
" <td>6.0</td>\n",
" <td>cape town, south africa</td>\n",
" <td>afrikaans5</td>\n",
" <td>afrikaans</td>\n",
" <td>male</td>\n",
" <td>1432</td>\n",
" <td>south africa</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>afrikaans5.wav</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" age age_onset birthplace filename \\\n",
"32 27.0 9.0 virginia, south africa afrikaans1 \n",
"33 40.0 5.0 pretoria, south africa afrikaans2 \n",
"34 43.0 4.0 pretoria, transvaal, south africa afrikaans3 \n",
"35 26.0 8.0 pretoria, south africa afrikaans4 \n",
"36 19.0 6.0 cape town, south africa afrikaans5 \n",
"\n",
" native_language sex speakerid country file_missing? \\\n",
"32 afrikaans female 1 south africa False \n",
"33 afrikaans male 2 south africa False \n",
"34 afrikaans male 418 south africa False \n",
"35 afrikaans male 1159 south africa False \n",
"36 afrikaans male 1432 south africa False \n",
"\n",
" Unnamed: 9 Unnamed: 10 Unnamed: 11 id \n",
"32 NaN NaN NaN afrikaans1.wav \n",
"33 NaN NaN NaN afrikaans2.wav \n",
"34 NaN NaN NaN afrikaans3.wav \n",
"35 NaN NaN NaN afrikaans4.wav \n",
"36 NaN NaN NaN afrikaans5.wav "
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"df['label'] = \"Please call Stella. Ask her to bring these things with her from the store: Six spoons of fresh snow peas, five thick slabs of blue cheese, and maybe a snack for her brother Bob. We also need a small plastic snake and a big toy frog for the kids. She can scoop these things into three red bags, and we will go meet her Wednesday at the train station.\""
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['age', 'age_onset', 'birthplace', 'filename', 'native_language', 'sex',\n",
" 'speakerid', 'country', 'file_missing?', 'Unnamed: 9', 'Unnamed: 10',\n",
" 'Unnamed: 11', 'id', 'label'],\n",
" dtype='object')"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"df = df.drop(\"Unnamed: 9\", axis=1)\n",
"df = df.drop(\"Unnamed: 10\", axis=1)\n",
"df = df.drop(\"Unnamed: 11\", axis=1)\n",
"df = df.drop(\"file_missing?\", axis=1)\n",
"df = df.drop(\"filename\", axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"df.loc[df['sex'] == 'famale', 'sex'] = 'female'"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"import pycountry_convert as pc\n",
"\n",
"def country_to_continent(country_name):\n",
" try:\n",
" country_alpha2 = pc.country_name_to_country_alpha2(country_name, cn_name_format=pc.COUNTRY_NAME_FORMAT_LOWER)\n",
" country_continent_code = pc.country_alpha2_to_continent_code(country_alpha2)\n",
" country_continent_name = pc.convert_continent_code_to_continent_name(country_continent_code)\n",
" return country_continent_name\n",
" except:\n",
" return None\n",
"\n",
"df[\"continent\"] = df[\"country\"].map(lambda x: country_to_continent(x))"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"False 1647\n",
"True 493\n",
"Name: continent, dtype: int64"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[\"continent\"].isnull().value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
"df = df.drop([1544, 1771])"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
"df.to_csv(\"metadata.csv\", index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Whisper"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|███████████████████████████████████████| 139M/139M [00:04<00:00, 30.3MiB/s]\n"
]
}
],
"source": [
"import whisper\n",
"model = whisper.load_model(\"base\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/anaconda3/lib/python3.8/site-packages/whisper/transcribe.py:78: UserWarning: FP16 is not supported on CPU; using FP32 instead\n",
" warnings.warn(\"FP16 is not supported on CPU; using FP32 instead\")\n"
]
},
{
"ename": "TypeError",
"evalue": "expected np.ndarray (got list)",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m/var/folders/tq/kqg2ct9d123gd0wmshf2bd3r0000gp/T/ipykernel_157/3894641212.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtranscribe\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"/Users/acabrera/dev/data/speech-accent-archive/recordings/recordings/afrikaans1.wav\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"/Users/acabrera/dev/data/speech-accent-archive/recordings/recordings/afrikaans1.wav\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m/opt/anaconda3/lib/python3.8/site-packages/whisper/transcribe.py\u001b[0m in \u001b[0;36mtranscribe\u001b[0;34m(model, audio, verbose, temperature, compression_ratio_threshold, logprob_threshold, no_speech_threshold, condition_on_previous_text, **decode_options)\u001b[0m\n\u001b[1;32m 82\u001b[0m \u001b[0mdecode_options\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"fp16\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 83\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 84\u001b[0;31m \u001b[0mmel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlog_mel_spectrogram\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maudio\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 85\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 86\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdecode_options\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"language\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/anaconda3/lib/python3.8/site-packages/whisper/audio.py\u001b[0m in \u001b[0;36mlog_mel_spectrogram\u001b[0;34m(audio, n_mels)\u001b[0m\n\u001b[1;32m 110\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maudio\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 111\u001b[0m \u001b[0maudio\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_audio\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maudio\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 112\u001b[0;31m \u001b[0maudio\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_numpy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maudio\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 113\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 114\u001b[0m \u001b[0mwindow\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhann_window\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mN_FFT\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maudio\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mTypeError\u001b[0m: expected np.ndarray (got list)"
]
}
],
"source": [
"result = model.transcribe([\"/Users/acabrera/dev/data/speech-accent-archive/recordings/recordings/afrikaans1.wav\", \"/Users/acabrera/dev/data/speech-accent-archive/recordings/recordings/afrikaans1.wav\"])"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' Please call Stella, ask her to bring these things with her from the store. 6 spoons of fresh snow peas, 5 thick slabs of blue cheese and maybe a snack for her brother Bob. We also need a small plastic snake and a big twig frog for the kids. She can scoop these things into free-rate bags and we will go meet a wind state train station.'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result[\"text\"]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.8.12 ('base')",
"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": "3.8.12"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "40d3a090f54c6569ab1632332b64b2c03c39dcf918b08424e98f38b5ae0af88f"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|