File size: 11,883 Bytes
2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 c82a77a 2ea8870 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "451d890e",
"metadata": {},
"outputs": [],
"source": [
"from datasets import load_dataset"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "eb0e4037",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3451cb7648e349cbbbdea3b672207ef7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading: 0%| | 0.00/1.68k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using custom data configuration chmanoj--ai4bharat__samanantar_processed_te-ec4e27c180ab4035\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading and preparing dataset samanantar/te (download: 292.93 MiB, generated: 678.62 MiB, post-processed: Unknown size, total: 971.55 MiB) to /workspace/cache/hf/datasets/parquet/chmanoj--ai4bharat__samanantar_processed_te-ec4e27c180ab4035/0.0.0/1638526fd0e8d960534e2155dc54fdff8dce73851f21f031d2fb9c2cf757c121...\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "68ea006ea9b943c3af2ed5ee7bb9fffb",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/1 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b5276db8e4614107ad0bdfe67ccca2fd",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading: 0%| | 0.00/151M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "0d3e27b107e7401dbe7f5dad8aa7ec08",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading: 0%| | 0.00/156M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ead9e8fde9a842b295955332ecae540d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/1 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dataset parquet downloaded and prepared to /workspace/cache/hf/datasets/parquet/chmanoj--ai4bharat__samanantar_processed_te-ec4e27c180ab4035/0.0.0/1638526fd0e8d960534e2155dc54fdff8dce73851f21f031d2fb9c2cf757c121. Subsequent calls will reuse this data.\n"
]
}
],
"source": [
"dataset = load_dataset(f\"chmanoj/ai4bharat__samanantar_processed_te\", split=\"train\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "e4f4f4e8",
"metadata": {},
"outputs": [],
"source": [
"with open(\"kenlm_text_te.txt\", \"w\") as file:\n",
" file.write(\" \".join(dataset[\"text\"]))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6e8a0e84",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 5,
"id": "5dfbf3e1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'/workspace/kenlm_te/src'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import os\n",
"os.getcwd()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "494bec1a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=== 1/5 Counting and sorting n-grams ===\n",
"Reading /workspace/kenlm_te/src/kenlm_text_te.txt\n",
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"****************************************************************************************************\n",
"Unigram tokens 32852369 types 1308846\n",
"=== 2/5 Calculating and sorting adjusted counts ===\n",
"Chain sizes: 1:15706152 2:51606089728 3:96761421824\n",
"Statistics:\n",
"1 1308845 D1=0.726852 D2=1.02775 D3+=1.30996\n",
"2 12720239 D1=0.818931 D2=1.12897 D3+=1.32699\n",
"3 23789023 D1=0.823705 D2=1.50814 D3+=1.24837\n",
"Memory estimate for binary LM:\n",
"type MB\n",
"probing 731 assuming -p 1.5\n",
"probing 809 assuming -r models -p 1.5\n",
"trie 342 without quantization\n",
"trie 206 assuming -q 8 -b 8 quantization \n",
"trie 316 assuming -a 22 array pointer compression\n",
"trie 180 assuming -a 22 -q 8 -b 8 array pointer compression and quantization\n",
"=== 3/5 Calculating and sorting initial probabilities ===\n",
"Chain sizes: 1:15706140 2:203523824 3:475780460\n",
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"####################################################################################################\n",
"=== 4/5 Calculating and writing order-interpolated probabilities ===\n",
"Chain sizes: 1:15706140 2:203523824 3:475780460\n",
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"####################################################################################################\n",
"=== 5/5 Writing ARPA model ===\n",
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"****************************************************************************************************\n",
"Name:lmplz\tVmPeak:145080616 kB\tVmRSS:38292 kB\tRSSMax:33928732 kB\tuser:43.6485\tsys:27.5682\tCPU:71.2168\treal:64.983\n"
]
}
],
"source": [
"!../../kenlm/build/bin/lmplz -o 3 <\"kenlm_text_te.txt\" > \"../3gram.arpa\""
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "c2c8c8ce",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=== 1/5 Counting and sorting n-grams ===\n",
"Reading /workspace/kenlm_te/src/kenlm_text_te.txt\n",
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"****************************************************************************************************\n",
"Unigram tokens 32852369 types 1308846\n",
"=== 2/5 Calculating and sorting adjusted counts ===\n",
"Chain sizes: 1:15706152 2:14474877952 3:27140399104 4:43424632832 5:63327596544\n",
"Statistics:\n",
"1 1308845 D1=0.726852 D2=1.02775 D3+=1.30996\n",
"2 12720239 D1=0.818931 D2=1.12897 D3+=1.32699\n",
"3 23789023 D1=0.910002 D2=1.27136 D3+=1.38596\n",
"4 28332665 D1=0.955371 D2=1.42566 D3+=1.4677\n",
"5 30063763 D1=0.898851 D2=1.71714 D3+=1.29889\n",
"Memory estimate for binary LM:\n",
"type MB\n",
"probing 2032 assuming -p 1.5\n",
"probing 2408 assuming -r models -p 1.5\n",
"trie 1058 without quantization\n",
"trie 613 assuming -q 8 -b 8 quantization \n",
"trie 921 assuming -a 22 array pointer compression\n",
"trie 476 assuming -a 22 -q 8 -b 8 array pointer compression and quantization\n",
"=== 3/5 Calculating and sorting initial probabilities ===\n",
"Chain sizes: 1:15706140 2:203523824 3:475780460 4:679983960 5:841785364\n",
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"####################################################################################################\n",
"=== 4/5 Calculating and writing order-interpolated probabilities ===\n",
"Chain sizes: 1:15706140 2:203523824 3:475780460 4:679983960 5:841785364\n",
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"####################################################################################################\n",
"=== 5/5 Writing ARPA model ===\n",
"----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100\n",
"****************************************************************************************************\n",
"Name:lmplz\tVmPeak:145104204 kB\tVmRSS:38296 kB\tRSSMax:26419104 kB\tuser:89.0779\tsys:42.0565\tCPU:131.134\treal:97.4678\n"
]
}
],
"source": [
"!../../kenlm/build/bin/lmplz -o 5 <\"kenlm_text_te.txt\" > \"../5gram.arpa\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "62b727b7",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 10,
"id": "c27f1ef3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 19.1 s, sys: 3.81 s, total: 22.9 s\n",
"Wall time: 22.9 s\n"
]
}
],
"source": [
"%%time\n",
"with open(\"../3gram.arpa\", \"r\") as read_file, open(\"../3gram_correct.arpa\", \"w\") as write_file:\n",
" has_added_eos = False\n",
" for line in read_file:\n",
" if not has_added_eos and \"ngram 1=\" in line:\n",
" count=line.strip().split(\"=\")[-1]\n",
" write_file.write(line.replace(f\"{count}\", f\"{int(count)+1}\"))\n",
" elif not has_added_eos and \"<s>\" in line:\n",
" write_file.write(line)\n",
" write_file.write(line.replace(\"<s>\", \"</s>\"))\n",
" has_added_eos = True\n",
" else:\n",
" write_file.write(line)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "8c8d963b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 1min 5s, sys: 12.8 s, total: 1min 18s\n",
"Wall time: 1min 18s\n"
]
}
],
"source": [
"%%time\n",
"with open(\"../5gram.arpa\", \"r\") as read_file, open(\"../5gram_correct.arpa\", \"w\") as write_file:\n",
" has_added_eos = False\n",
" for line in read_file:\n",
" if not has_added_eos and \"ngram 1=\" in line:\n",
" count=line.strip().split(\"=\")[-1]\n",
" write_file.write(line.replace(f\"{count}\", f\"{int(count)+1}\"))\n",
" elif not has_added_eos and \"<s>\" in line:\n",
" write_file.write(line)\n",
" write_file.write(line.replace(\"<s>\", \"</s>\"))\n",
" has_added_eos = True\n",
" else:\n",
" write_file.write(line)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9447691c",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "95d50071",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.8.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|