File size: 59,739 Bytes
becc14c | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 | {
"cells": [
{
"cell_type": "markdown",
"source": [
"## Predspracovanie dát\n",
"\n",
"Pomocné funkcie využité pre vytvorenie trénovacieho/evaluačného datasetu v tomto notebooku, predspracovávali dáta kombináciou delenia audia na menšie časti na základe detekovania ticha v nahrávkach, resampling dát na 16kHz formát požadovaný modelom, automatickú trasnkripciu ladeným modelom s prvotných tréningov, a navrhnutie rozdelenia nahrávok podľa počtu tokenov na ukončené vety.\n",
"\n",
"### Výstupný formát\n",
"- TSV súbor obsahujúci:\n",
" - cestu k zvukovému záznamu\n",
" - dĺžku záznamu v sekundách\n",
" - transkripciu záznamu\n",
"\n",
"\n",
"### Využité knižnice\n",
" - os\n",
" - torch\n",
" - torchaudio - Na načitanie a resampling zvukových záznamov\n",
" - pydub (AudioSegment, silence)\t- Na spracovanie audia, detekciu ticha, exportovanie častí\n",
" - transformers -\tNa načítanie procesora, modelu, a tokenizáciu pre transkripciu\n",
" - re - Regulárne výrazy na rozdelenie textu podľa viet.\n",
" - pandas - export dát do TSV\n",
" - tqdm - monitorovanie priebehu pri spracovaní tokenov\n",
"\n",
"\n"
],
"metadata": {
"id": "dB-uebOX2p8j"
}
},
{
"cell_type": "markdown",
"source": [
"## Popis funckii\n",
"\n",
"### load_whisper_custom_model\n",
"- **Parametre :** cesta k modelu\n",
"- načitanie vlastného modelu pomocou transformers\n",
"- použitie WhisperProcessor a WhisperForConditionalGeneration\n",
"- prenesenie modelu na GPU\n",
"\n",
"### transcribe_function\n",
"- **Parametre :** cesta k súboru so zvukovým záznamom, processor, model\n",
"- Načítanie audia pomocou torchaudio.load.\n",
"- Ak sampling rate audia ≠ 16000 Hz (cieľ), resampluje sa pomocou torchaudio.transforms.Resample.\n",
"- Audio sa premení na vstupné features cez processor.feature_extractor.\n",
"- Forced decoding nastavuje jazyk (\"sk\" = slovenčina) a úlohu (\"transcribe\") cez get_decoder_prompt_ids.\n",
"- Model generuje text cez beam search (num_beams=5, skoré ukončenie).\n",
"- Výsledok sa dekóduje cez tokenizer a vráti čistý text.\n",
"\n",
"### split_text_by_sentence\n",
"- **Parametre :** text, maximálny počet tokenov, tokenizer\n",
"- používa regulárne výrazy na delenie textu po vetách (bodka, otáznik, výkričník)\n",
"- ak vetu už nemožno pridať do chunku bez prekročenia limitu tokenov (max_tokens), začne nový chunk\n",
"- okenizácia sa robí pomocou processor.tokenizer(sentence).input_ids\n",
"\n",
"\n",
"### split_and_transcribe_with_token_limit\n",
"- **Parametre :** cesta k súboru so zvukovým záznamom, processor, model\n",
"- načítanie audia cez pydub (AudioSegment.from_mp3).\n",
"- detekcia ticha:\n",
" - pomocou silence.detect_silence(audio, min_silence_len=MIN_SILENCE_LEN, silence_thresh=SILENCE_THRESH)\n",
" - detekované tiché body (v strede medzi začiatkom a koncom ticha) sa berú ako potenciálne body delenia\n",
"- fallback rozdelenie pre dlhé časti (> MAX_CHUNK_MS):\n",
"- ak chunk je príliš dlhý, skúsi sa ešte jemnejšie delenie s mäkšími kritériami (ALT_MIN_SILENCE_LEN).\n",
"- export chunkov do .wav formátu.\n",
"- transkripcia chunkov\n",
"- v prípade, že text presahuje token limit, text sa rozdelí na viac častí (iba textové rozdelenie).\n",
"\n",
"\n",
"### process_all_mp3\n",
"- spracovanie všetkých súborov vo formáte mp3 v definovanom priečinku\n",
"- volá funkcie na spracovanie dát\n",
"- výstup TSV súbor vo formáte : **path**, **duration**, **sentence**"
],
"metadata": {
"id": "MV7Dh_Qw-nWV"
}
},
{
"cell_type": "markdown",
"source": [
"## Import knižníc"
],
"metadata": {
"id": "Ybedar-N-957"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "kDNwj9t1qm8w",
"outputId": "12aca0b1-41c4-4eeb-9dc7-f13a057bde20",
"collapsed": true
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting pydub\n",
" Downloading pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
"Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
"Installing collected packages: pydub\n",
"Successfully installed pydub-0.25.1\n"
]
}
],
"source": [
"!pip install pydub"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "D2MGL2U4q8Iu"
},
"outputs": [],
"source": [
"import os\n",
"import pandas as pd\n",
"import nltk\n",
"from pydub import AudioSegment, silence\n",
"from nltk.tokenize import sent_tokenize\n",
"import re\n",
"import gc\n",
"import torch\n",
"import torchaudio\n",
"import pandas as pd\n",
"import soundfile as sf\n",
"from tqdm import tqdm\n",
"from pydub import AudioSegment, silence\n",
"from transformers import WhisperProcessor, WhisperForConditionalGeneration"
]
},
{
"cell_type": "markdown",
"source": [
"## Import vlastného modelu implemenácia funkcií\n"
],
"metadata": {
"id": "ynqsRY58V1ts"
}
},
{
"cell_type": "code",
"source": [
"from google.colab import drive\n",
"\n",
"drive.mount('/content/drive')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "wiQ3EoJwV6c9",
"outputId": "6218351e-5d3b-47c8-a6dc-e0bec12abf1a"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# === CONFIG ===\n",
"\n",
"AUDIO_FOLDER = \"/content/drive/MyDrive/DP_data/audio_files\"\n",
"OUTPUT_FOLDER = \"/content/drive/MyDrive/DP_data/audio_chunks\"\n",
"TSV_OUTPUT = \"/content/drive/MyDrive/DP_data/adpocia3.tsv\"\n",
"MODEL_DIR = \"/content/drive/MyDrive/DP_data/whisper_medium_3d\"\n",
"\n",
"TARGET_SAMPLE_RATE = 16000\n",
"TOKEN_LIMIT = 100\n",
"MIN_SILENCE_LEN = 400 # Minimum silence length v ms\n",
"SILENCE_THRESH = -40 # Silence threshold v dB\n",
"\n",
"MAX_CHUNK_MS = 28000\n",
"ALT_MIN_SILENCE_LEN = 200 # mäkšie kritérium pre fallback\n",
"\n",
"os.makedirs(OUTPUT_FOLDER, exist_ok=True)\n",
"\n",
"# ==== NACITANIE MODELU ====\n",
"def load_whisper_custom_model(model_dir):\n",
" processor = WhisperProcessor.from_pretrained(model_dir)\n",
" model = WhisperForConditionalGeneration.from_pretrained(model_dir)\n",
" model.eval()\n",
" model.to(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
" return processor, model\n",
"\n",
"# ==== TRANSKRIPCIA ====\n",
"def transcribe_function(path_file, processor, model):\n",
" speech_array, sampling_rate = torchaudio.load(path_file)\n",
" if sampling_rate != TARGET_SAMPLE_RATE:\n",
" resampler = torchaudio.transforms.Resample(orig_freq=sampling_rate, new_freq=TARGET_SAMPLE_RATE)\n",
" speech_array = resampler(speech_array)\n",
"\n",
" inputs = processor.feature_extractor(\n",
" speech_array.squeeze().numpy(),\n",
" sampling_rate=TARGET_SAMPLE_RATE,\n",
" return_tensors=\"pt\"\n",
" )\n",
"\n",
" forced_decoder_ids = processor.get_decoder_prompt_ids(language=\"sk\", task=\"transcribe\")\n",
" input_features = inputs[\"input_features\"].to(model.device)\n",
"\n",
" with torch.no_grad():\n",
" generated_ids = model.generate(\n",
" input_features,\n",
" forced_decoder_ids=forced_decoder_ids,\n",
" num_beams=5,\n",
" early_stopping=True\n",
" )\n",
"\n",
" transcription = processor.tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]\n",
" return transcription.strip()\n",
"\n",
"# ==== DELENIE TEXTU PODLA VIET ====\n",
"def split_text_by_sentence(text, max_tokens, tokenizer):\n",
" sentences = re.split(r'(?<=[.!?])\\s+', text.strip())\n",
" chunks, current_chunk, current_tokens = [], [], 0\n",
"\n",
" for sentence in sentences:\n",
" tokens = tokenizer(sentence).input_ids\n",
" if current_tokens + len(tokens) > max_tokens and current_chunk:\n",
" chunks.append(\" \".join(current_chunk))\n",
" current_chunk = [sentence]\n",
" current_tokens = len(tokens)\n",
" else:\n",
" current_chunk.append(sentence)\n",
" current_tokens += len(tokens)\n",
"\n",
" if current_chunk:\n",
" chunks.append(\" \".join(current_chunk))\n",
"\n",
" return chunks\n",
"\n",
"def split_and_transcribe_with_token_limit(mp3_path, processor, model):\n",
" audio = AudioSegment.from_mp3(mp3_path)\n",
" filename = os.path.splitext(os.path.basename(mp3_path))[0]\n",
"\n",
" silence_points = silence.detect_silence(audio, min_silence_len=MIN_SILENCE_LEN, silence_thresh=SILENCE_THRESH)\n",
" silence_points = [((start + end) // 2) for start, end in silence_points]\n",
"\n",
" chunk_starts = [0]\n",
" for point in silence_points:\n",
" if point - chunk_starts[-1] >= 20000:\n",
" chunk_starts.append(point)\n",
" chunk_starts.append(len(audio))\n",
"\n",
" adjusted_starts = [chunk_starts[0]]\n",
" for i in range(1, len(chunk_starts)):\n",
" prev = adjusted_starts[-1]\n",
" curr = chunk_starts[i]\n",
" duration = curr - prev\n",
"\n",
" if duration > MAX_CHUNK_MS:\n",
" long_chunk = audio[prev:curr]\n",
" extra_silences = silence.detect_silence(\n",
" long_chunk, min_silence_len=ALT_MIN_SILENCE_LEN, silence_thresh=SILENCE_THRESH\n",
" )\n",
" extra_points = [((start + end) // 2 + prev) for start, end in extra_silences if (start + end)//2 + prev < curr]\n",
"\n",
" if extra_points:\n",
" for p in extra_points:\n",
" if p - adjusted_starts[-1] >= 8000:\n",
" adjusted_starts.append(p)\n",
" if adjusted_starts[-1] != curr:\n",
" adjusted_starts.append(curr)\n",
" else:\n",
" adjusted_starts.append(curr)\n",
" else:\n",
" adjusted_starts.append(curr)\n",
"\n",
" # Transkripcia a tokenové delenie\n",
" rows = []\n",
" chunk_index = 0\n",
"\n",
" for i in range(len(adjusted_starts) - 1):\n",
" start, end = adjusted_starts[i], adjusted_starts[i + 1]\n",
" chunk = audio[start:end]\n",
" chunk_path = os.path.join(OUTPUT_FOLDER, f\"{filename}_chunk_{chunk_index}.wav\")\n",
" chunk.export(chunk_path, format=\"wav\")\n",
"\n",
" transcription = transcribe_function(chunk_path, processor, model)\n",
" token_count = len(processor.tokenizer(transcription).input_ids)\n",
"\n",
" if token_count > TOKEN_LIMIT:\n",
" sub_chunks = split_text_by_sentence(transcription, TOKEN_LIMIT, processor.tokenizer)\n",
"\n",
" for j, sub_text in enumerate(sub_chunks):\n",
" # Vytvorenie navrhu rozdelenia povodneho chunk\n",
" new_path = f\"{filename}_chunk_{chunk_index}_p{j+1}.wav\"\n",
" rows.append([new_path, round((end - start)/1000, 3), sub_text])\n",
" else:\n",
" duration_sec = round((end - start) / 1000, 3)\n",
" rows.append([os.path.basename(chunk_path), duration_sec, transcription])\n",
"\n",
" chunk_index += 1\n",
"\n",
" return rows\n",
"\n",
"def process_all_mp3():\n",
"\n",
" all_rows = []\n",
" for file in tqdm(sorted(os.listdir(AUDIO_FOLDER))):\n",
" if file.endswith(\".mp3\"):\n",
" full_path = os.path.join(AUDIO_FOLDER, file)\n",
" rows = split_and_transcribe_with_token_limit(full_path, processor, model)\n",
" all_rows.extend(rows)\n",
"\n",
" df = pd.DataFrame(all_rows, columns=[\"path\", \"duration\", \"sentence\"])\n",
" df.to_csv(TSV_OUTPUT, sep=\"\\t\", index=False)\n",
" print(f\" TSV saved to: {TSV_OUTPUT}\")\n"
],
"metadata": {
"id": "9ZCdSEiplhyd"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"processor, model = load_whisper_custom_model(MODEL_DIR)"
],
"metadata": {
"id": "cSCPsy8RljSq"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"pip install git+https://github.com/m-bain/whisperx.git"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"collapsed": true,
"id": "xNvUOIGyyfF_",
"outputId": "5f89b7d6-e356-44b5-8d43-f1fcc63bb13c"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting git+https://github.com/m-bain/whisperx.git\n",
" Cloning https://github.com/m-bain/whisperx.git to /tmp/pip-req-build-y6876pd_\n",
" Running command git clone --filter=blob:none --quiet https://github.com/m-bain/whisperx.git /tmp/pip-req-build-y6876pd_\n",
" Resolved https://github.com/m-bain/whisperx.git to commit 0aed8745890f12ecfe0b2d9c4ba62bcdfb16f94e\n",
" Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting ctranslate2>=4.5.0 (from whisperx==3.3.1)\n",
" Downloading ctranslate2-4.6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (10 kB)\n",
"Collecting faster-whisper>=1.1.1 (from whisperx==3.3.1)\n",
" Downloading faster_whisper-1.1.1-py3-none-any.whl.metadata (16 kB)\n",
"Requirement already satisfied: nltk>=3.9.1 in /usr/local/lib/python3.11/dist-packages (from whisperx==3.3.1) (3.9.1)\n",
"Requirement already satisfied: numpy>=2.0.2 in /usr/local/lib/python3.11/dist-packages (from whisperx==3.3.1) (2.0.2)\n",
"Collecting onnxruntime==1.19 (from whisperx==3.3.1)\n",
" Downloading onnxruntime-1.19.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (4.3 kB)\n",
"Collecting pandas>=2.2.3 (from whisperx==3.3.1)\n",
" Downloading pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (89 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m89.9/89.9 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting pyannote-audio>=3.3.2 (from whisperx==3.3.1)\n",
" Downloading pyannote.audio-3.3.2-py2.py3-none-any.whl.metadata (11 kB)\n",
"Requirement already satisfied: torch>=2.5.1 in /usr/local/lib/python3.11/dist-packages (from whisperx==3.3.1) (2.6.0+cu124)\n",
"Requirement already satisfied: torchaudio>=2.5.1 in /usr/local/lib/python3.11/dist-packages (from whisperx==3.3.1) (2.6.0+cu124)\n",
"Requirement already satisfied: transformers>=4.48.0 in /usr/local/lib/python3.11/dist-packages (from whisperx==3.3.1) (4.51.3)\n",
"Collecting coloredlogs (from onnxruntime==1.19->whisperx==3.3.1)\n",
" Downloading coloredlogs-15.0.1-py2.py3-none-any.whl.metadata (12 kB)\n",
"Requirement already satisfied: flatbuffers in /usr/local/lib/python3.11/dist-packages (from onnxruntime==1.19->whisperx==3.3.1) (25.2.10)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from onnxruntime==1.19->whisperx==3.3.1) (24.2)\n",
"Requirement already satisfied: protobuf in /usr/local/lib/python3.11/dist-packages (from onnxruntime==1.19->whisperx==3.3.1) (5.29.4)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.11/dist-packages (from onnxruntime==1.19->whisperx==3.3.1) (1.13.1)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.11/dist-packages (from ctranslate2>=4.5.0->whisperx==3.3.1) (75.2.0)\n",
"Requirement already satisfied: pyyaml<7,>=5.3 in /usr/local/lib/python3.11/dist-packages (from ctranslate2>=4.5.0->whisperx==3.3.1) (6.0.2)\n",
"Requirement already satisfied: huggingface-hub>=0.13 in /usr/local/lib/python3.11/dist-packages (from faster-whisper>=1.1.1->whisperx==3.3.1) (0.30.2)\n",
"Requirement already satisfied: tokenizers<1,>=0.13 in /usr/local/lib/python3.11/dist-packages (from faster-whisper>=1.1.1->whisperx==3.3.1) (0.21.1)\n",
"Collecting av>=11 (from faster-whisper>=1.1.1->whisperx==3.3.1)\n",
" Downloading av-14.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.7 kB)\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from faster-whisper>=1.1.1->whisperx==3.3.1) (4.67.1)\n",
"Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from nltk>=3.9.1->whisperx==3.3.1) (8.1.8)\n",
"Requirement already satisfied: joblib in /usr/local/lib/python3.11/dist-packages (from nltk>=3.9.1->whisperx==3.3.1) (1.4.2)\n",
"Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.11/dist-packages (from nltk>=3.9.1->whisperx==3.3.1) (2024.11.6)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas>=2.2.3->whisperx==3.3.1) (2.9.0.post0)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=2.2.3->whisperx==3.3.1) (2025.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=2.2.3->whisperx==3.3.1) (2025.2)\n",
"Collecting asteroid-filterbanks>=0.4 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading asteroid_filterbanks-0.4.0-py3-none-any.whl.metadata (3.3 kB)\n",
"Requirement already satisfied: einops>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pyannote-audio>=3.3.2->whisperx==3.3.1) (0.8.1)\n",
"Collecting lightning>=2.0.1 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading lightning-2.5.1.post0-py3-none-any.whl.metadata (39 kB)\n",
"Collecting omegaconf<3.0,>=2.1 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading omegaconf-2.3.0-py3-none-any.whl.metadata (3.9 kB)\n",
"Collecting pyannote.core>=5.0.0 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading pyannote.core-5.0.0-py3-none-any.whl.metadata (1.4 kB)\n",
"Collecting pyannote.database>=5.0.1 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading pyannote.database-5.1.3-py3-none-any.whl.metadata (1.1 kB)\n",
"Collecting pyannote.metrics>=3.2 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading pyannote.metrics-3.2.1-py3-none-any.whl.metadata (1.3 kB)\n",
"Collecting pyannote.pipeline>=3.0.1 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading pyannote.pipeline-3.0.1-py3-none-any.whl.metadata (897 bytes)\n",
"Collecting pytorch-metric-learning>=2.1.0 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading pytorch_metric_learning-2.8.1-py3-none-any.whl.metadata (18 kB)\n",
"Requirement already satisfied: rich>=12.0.0 in /usr/local/lib/python3.11/dist-packages (from pyannote-audio>=3.3.2->whisperx==3.3.1) (13.9.4)\n",
"Collecting semver>=3.0.0 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading semver-3.0.4-py3-none-any.whl.metadata (6.8 kB)\n",
"Requirement already satisfied: soundfile>=0.12.1 in /usr/local/lib/python3.11/dist-packages (from pyannote-audio>=3.3.2->whisperx==3.3.1) (0.13.1)\n",
"Collecting speechbrain>=1.0.0 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading speechbrain-1.0.3-py3-none-any.whl.metadata (24 kB)\n",
"Collecting tensorboardX>=2.6 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading tensorboardX-2.6.2.2-py2.py3-none-any.whl.metadata (5.8 kB)\n",
"Collecting torch-audiomentations>=0.11.0 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading torch_audiomentations-0.12.0-py3-none-any.whl.metadata (15 kB)\n",
"Collecting torchmetrics>=0.11.0 (from pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading torchmetrics-1.7.1-py3-none-any.whl.metadata (21 kB)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (3.18.0)\n",
"Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (4.13.2)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (3.4.2)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (3.1.6)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (2025.3.2)\n",
"Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cublas-cu12==12.4.5.8 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cufft-cu12==11.2.1.3 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-curand-cu12==10.3.5.147 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (0.6.2)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (2.21.5)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (12.4.127)\n",
"Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch>=2.5.1->whisperx==3.3.1)\n",
" Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch>=2.5.1->whisperx==3.3.1) (3.2.0)\n",
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy->onnxruntime==1.19->whisperx==3.3.1) (1.3.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from transformers>=4.48.0->whisperx==3.3.1) (2.32.3)\n",
"Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from transformers>=4.48.0->whisperx==3.3.1) (0.5.3)\n",
"Collecting lightning-utilities<2.0,>=0.10.0 (from lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading lightning_utilities-0.14.3-py3-none-any.whl.metadata (5.6 kB)\n",
"Collecting pytorch-lightning (from lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading pytorch_lightning-2.5.1.post0-py3-none-any.whl.metadata (20 kB)\n",
"Collecting antlr4-python3-runtime==4.9.* (from omegaconf<3.0,>=2.1->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading antlr4-python3-runtime-4.9.3.tar.gz (117 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.0/117.0 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: sortedcontainers>=2.0.4 in /usr/local/lib/python3.11/dist-packages (from pyannote.core>=5.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1) (2.4.0)\n",
"Requirement already satisfied: scipy>=1.1 in /usr/local/lib/python3.11/dist-packages (from pyannote.core>=5.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.15.2)\n",
"Requirement already satisfied: typer>=0.12.1 in /usr/local/lib/python3.11/dist-packages (from pyannote.database>=5.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (0.15.2)\n",
"Requirement already satisfied: scikit-learn>=0.17.1 in /usr/local/lib/python3.11/dist-packages (from pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.6.1)\n",
"Collecting docopt>=0.6.2 (from pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading docopt-0.6.2.tar.gz (25 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: tabulate>=0.7.7 in /usr/local/lib/python3.11/dist-packages (from pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (0.9.0)\n",
"Requirement already satisfied: matplotlib>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (3.10.0)\n",
"Collecting optuna>=3.1 (from pyannote.pipeline>=3.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading optuna-4.3.0-py3-none-any.whl.metadata (17 kB)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas>=2.2.3->whisperx==3.3.1) (1.17.0)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich>=12.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1) (3.0.0)\n",
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich>=12.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1) (2.19.1)\n",
"Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.11/dist-packages (from soundfile>=0.12.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.17.1)\n",
"Collecting hyperpyyaml (from speechbrain>=1.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading HyperPyYAML-1.2.2-py3-none-any.whl.metadata (7.6 kB)\n",
"Requirement already satisfied: sentencepiece in /usr/local/lib/python3.11/dist-packages (from speechbrain>=1.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1) (0.2.0)\n",
"Collecting julius<0.3,>=0.2.3 (from torch-audiomentations>=0.11.0->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading julius-0.2.7.tar.gz (59 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.6/59.6 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting torch-pitch-shift>=1.2.2 (from torch-audiomentations>=0.11.0->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading torch_pitch_shift-1.2.5-py3-none-any.whl.metadata (2.5 kB)\n",
"Collecting humanfriendly>=9.1 (from coloredlogs->onnxruntime==1.19->whisperx==3.3.1)\n",
" Downloading humanfriendly-10.0-py2.py3-none-any.whl.metadata (9.2 kB)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch>=2.5.1->whisperx==3.3.1) (3.0.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->transformers>=4.48.0->whisperx==3.3.1) (3.4.1)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->transformers>=4.48.0->whisperx==3.3.1) (3.10)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->transformers>=4.48.0->whisperx==3.3.1) (2.4.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->transformers>=4.48.0->whisperx==3.3.1) (2025.1.31)\n",
"Requirement already satisfied: pycparser in /usr/local/lib/python3.11/dist-packages (from cffi>=1.0->soundfile>=0.12.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (2.22)\n",
"Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (3.11.15)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich>=12.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1) (0.1.2)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.3.2)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (4.57.0)\n",
"Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.4.8)\n",
"Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (11.2.1)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (3.2.3)\n",
"Collecting alembic>=1.5.0 (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading alembic-1.15.2-py3-none-any.whl.metadata (7.3 kB)\n",
"Collecting colorlog (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading colorlog-6.9.0-py3-none-any.whl.metadata (10 kB)\n",
"Requirement already satisfied: sqlalchemy>=1.4.2 in /usr/local/lib/python3.11/dist-packages (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (2.0.40)\n",
"Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn>=0.17.1->pyannote.metrics>=3.2->pyannote-audio>=3.3.2->whisperx==3.3.1) (3.6.0)\n",
"Collecting primePy>=1.3 (from torch-pitch-shift>=1.2.2->torch-audiomentations>=0.11.0->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading primePy-1.3-py3-none-any.whl.metadata (4.8 kB)\n",
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.11/dist-packages (from typer>=0.12.1->pyannote.database>=5.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.5.4)\n",
"Collecting ruamel.yaml>=0.17.28 (from hyperpyyaml->speechbrain>=1.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading ruamel.yaml-0.18.10-py3-none-any.whl.metadata (23 kB)\n",
"Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (2.6.1)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.3.2)\n",
"Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (25.3.0)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.6.0)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (6.4.3)\n",
"Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (0.3.1)\n",
"Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.20.0)\n",
"Requirement already satisfied: Mako in /usr/lib/python3/dist-packages (from alembic>=1.5.0->optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (1.1.3)\n",
"Collecting ruamel.yaml.clib>=0.2.7 (from ruamel.yaml>=0.17.28->hyperpyyaml->speechbrain>=1.0.0->pyannote-audio>=3.3.2->whisperx==3.3.1)\n",
" Downloading ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.7 kB)\n",
"Requirement already satisfied: greenlet>=1 in /usr/local/lib/python3.11/dist-packages (from sqlalchemy>=1.4.2->optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote-audio>=3.3.2->whisperx==3.3.1) (3.2.1)\n",
"Downloading onnxruntime-1.19.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (13.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.2/13.2 MB\u001b[0m \u001b[31m103.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading ctranslate2-4.6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.6/38.6 MB\u001b[0m \u001b[31m16.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading faster_whisper-1.1.1-py3-none-any.whl (1.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m60.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.1/13.1 MB\u001b[0m \u001b[31m126.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyannote.audio-3.3.2-py2.py3-none-any.whl (898 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m898.7/898.7 kB\u001b[0m \u001b[31m58.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m70.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m37.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m54.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m14.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m7.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m76.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading asteroid_filterbanks-0.4.0-py3-none-any.whl (29 kB)\n",
"Downloading av-14.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (35.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m35.2/35.2 MB\u001b[0m \u001b[31m16.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading lightning-2.5.1.post0-py3-none-any.whl (819 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m819.0/819.0 kB\u001b[0m \u001b[31m49.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading omegaconf-2.3.0-py3-none-any.whl (79 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.5/79.5 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyannote.core-5.0.0-py3-none-any.whl (58 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.5/58.5 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyannote.database-5.1.3-py3-none-any.whl (48 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m48.1/48.1 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyannote.metrics-3.2.1-py3-none-any.whl (51 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.4/51.4 kB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyannote.pipeline-3.0.1-py3-none-any.whl (31 kB)\n",
"Downloading pytorch_metric_learning-2.8.1-py3-none-any.whl (125 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m125.9/125.9 kB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading semver-3.0.4-py3-none-any.whl (17 kB)\n",
"Downloading speechbrain-1.0.3-py3-none-any.whl (864 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m864.1/864.1 kB\u001b[0m \u001b[31m51.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading tensorboardX-2.6.2.2-py2.py3-none-any.whl (101 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m101.7/101.7 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading torch_audiomentations-0.12.0-py3-none-any.whl (48 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m48.5/48.5 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading torchmetrics-1.7.1-py3-none-any.whl (961 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m961.5/961.5 kB\u001b[0m \u001b[31m55.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m4.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading lightning_utilities-0.14.3-py3-none-any.whl (28 kB)\n",
"Downloading optuna-4.3.0-py3-none-any.whl (386 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m386.6/386.6 kB\u001b[0m \u001b[31m33.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading torch_pitch_shift-1.2.5-py3-none-any.whl (5.0 kB)\n",
"Downloading HyperPyYAML-1.2.2-py3-none-any.whl (16 kB)\n",
"Downloading pytorch_lightning-2.5.1.post0-py3-none-any.whl (823 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.1/823.1 kB\u001b[0m \u001b[31m54.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading alembic-1.15.2-py3-none-any.whl (231 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m231.9/231.9 kB\u001b[0m \u001b[31m23.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading primePy-1.3-py3-none-any.whl (4.0 kB)\n",
"Downloading ruamel.yaml-0.18.10-py3-none-any.whl (117 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.7/117.7 kB\u001b[0m \u001b[31m11.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading colorlog-6.9.0-py3-none-any.whl (11 kB)\n",
"Downloading ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (739 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m739.1/739.1 kB\u001b[0m \u001b[31m52.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hBuilding wheels for collected packages: whisperx, antlr4-python3-runtime, docopt, julius\n",
" Building wheel for whisperx (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for whisperx: filename=whisperx-3.3.1-py3-none-any.whl size=16482009 sha256=ce99924c11e21b4f22fc01e88822fc918268d56bd7f675119ccdf611d1f78640\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-l7xwr65x/wheels/a7/c5/cb/f337e8d88ff15af9ece963912a153e4132d00e7cdd61f48416\n",
" Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for antlr4-python3-runtime: filename=antlr4_python3_runtime-4.9.3-py3-none-any.whl size=144554 sha256=b51000eededb4a85c6a278733c1a114ae6ffe6d4761728c5c5a60d8a5fe3c45e\n",
" Stored in directory: /root/.cache/pip/wheels/1a/97/32/461f837398029ad76911109f07047fde1d7b661a147c7c56d1\n",
" Building wheel for docopt (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=9da05d25e10ee22a692e794b10e0ddb5a5740525a248a2b6bab8281a4a6f3dfe\n",
" Stored in directory: /root/.cache/pip/wheels/1a/b0/8c/4b75c4116c31f83c8f9f047231251e13cc74481cca4a78a9ce\n",
" Building wheel for julius (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for julius: filename=julius-0.2.7-py3-none-any.whl size=21870 sha256=e53b0a316db08563d285c0acba335e19c47be9589ec9f5ede7aafdb611fd9436\n",
" Stored in directory: /root/.cache/pip/wheels/16/15/d4/edd724cefe78050a6ba3344b8b0c6672db829a799dbb9f81ff\n",
"Successfully built whisperx antlr4-python3-runtime docopt julius\n",
"Installing collected packages: primePy, docopt, antlr4-python3-runtime, tensorboardX, semver, ruamel.yaml.clib, omegaconf, nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, lightning-utilities, humanfriendly, ctranslate2, colorlog, av, ruamel.yaml, pyannote.core, pandas, nvidia-cusparse-cu12, nvidia-cudnn-cu12, coloredlogs, alembic, optuna, onnxruntime, nvidia-cusolver-cu12, hyperpyyaml, pyannote.database, faster-whisper, torchmetrics, pytorch-metric-learning, pyannote.pipeline, pyannote.metrics, julius, asteroid-filterbanks, torch-pitch-shift, speechbrain, pytorch-lightning, torch-audiomentations, lightning, pyannote-audio, whisperx\n",
" Attempting uninstall: nvidia-nvjitlink-cu12\n",
" Found existing installation: nvidia-nvjitlink-cu12 12.5.82\n",
" Uninstalling nvidia-nvjitlink-cu12-12.5.82:\n",
" Successfully uninstalled nvidia-nvjitlink-cu12-12.5.82\n",
" Attempting uninstall: nvidia-curand-cu12\n",
" Found existing installation: nvidia-curand-cu12 10.3.6.82\n",
" Uninstalling nvidia-curand-cu12-10.3.6.82:\n",
" Successfully uninstalled nvidia-curand-cu12-10.3.6.82\n",
" Attempting uninstall: nvidia-cufft-cu12\n",
" Found existing installation: nvidia-cufft-cu12 11.2.3.61\n",
" Uninstalling nvidia-cufft-cu12-11.2.3.61:\n",
" Successfully uninstalled nvidia-cufft-cu12-11.2.3.61\n",
" Attempting uninstall: nvidia-cuda-runtime-cu12\n",
" Found existing installation: nvidia-cuda-runtime-cu12 12.5.82\n",
" Uninstalling nvidia-cuda-runtime-cu12-12.5.82:\n",
" Successfully uninstalled nvidia-cuda-runtime-cu12-12.5.82\n",
" Attempting uninstall: nvidia-cuda-nvrtc-cu12\n",
" Found existing installation: nvidia-cuda-nvrtc-cu12 12.5.82\n",
" Uninstalling nvidia-cuda-nvrtc-cu12-12.5.82:\n",
" Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.5.82\n",
" Attempting uninstall: nvidia-cuda-cupti-cu12\n",
" Found existing installation: nvidia-cuda-cupti-cu12 12.5.82\n",
" Uninstalling nvidia-cuda-cupti-cu12-12.5.82:\n",
" Successfully uninstalled nvidia-cuda-cupti-cu12-12.5.82\n",
" Attempting uninstall: nvidia-cublas-cu12\n",
" Found existing installation: nvidia-cublas-cu12 12.5.3.2\n",
" Uninstalling nvidia-cublas-cu12-12.5.3.2:\n",
" Successfully uninstalled nvidia-cublas-cu12-12.5.3.2\n",
" Attempting uninstall: pandas\n",
" Found existing installation: pandas 2.2.2\n",
" Uninstalling pandas-2.2.2:\n",
" Successfully uninstalled pandas-2.2.2\n",
" Attempting uninstall: nvidia-cusparse-cu12\n",
" Found existing installation: nvidia-cusparse-cu12 12.5.1.3\n",
" Uninstalling nvidia-cusparse-cu12-12.5.1.3:\n",
" Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3\n",
" Attempting uninstall: nvidia-cudnn-cu12\n",
" Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n",
" Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n",
" Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n",
" Attempting uninstall: nvidia-cusolver-cu12\n",
" Found existing installation: nvidia-cusolver-cu12 11.6.3.83\n",
" Uninstalling nvidia-cusolver-cu12-11.6.3.83:\n",
" Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83\n",
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"google-colab 1.0.0 requires pandas==2.2.2, but you have pandas 2.2.3 which is incompatible.\u001b[0m\u001b[31m\n",
"\u001b[0mSuccessfully installed alembic-1.15.2 antlr4-python3-runtime-4.9.3 asteroid-filterbanks-0.4.0 av-14.3.0 coloredlogs-15.0.1 colorlog-6.9.0 ctranslate2-4.6.0 docopt-0.6.2 faster-whisper-1.1.1 humanfriendly-10.0 hyperpyyaml-1.2.2 julius-0.2.7 lightning-2.5.1.post0 lightning-utilities-0.14.3 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 omegaconf-2.3.0 onnxruntime-1.19.0 optuna-4.3.0 pandas-2.2.3 primePy-1.3 pyannote-audio-3.3.2 pyannote.core-5.0.0 pyannote.database-5.1.3 pyannote.metrics-3.2.1 pyannote.pipeline-3.0.1 pytorch-lightning-2.5.1.post0 pytorch-metric-learning-2.8.1 ruamel.yaml-0.18.10 ruamel.yaml.clib-0.2.12 semver-3.0.4 speechbrain-1.0.3 tensorboardX-2.6.2.2 torch-audiomentations-0.12.0 torch-pitch-shift-1.2.5 torchmetrics-1.7.1 whisperx-3.3.1\n"
]
},
{
"output_type": "display_data",
"data": {
"application/vnd.colab-display-data+json": {
"pip_warning": {
"packages": [
"nvidia",
"pydevd_plugins"
]
},
"id": "1fe374a7d4d44a3fa775a6ea8224e42e"
}
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"## Spracovanie zvukového záznamu"
],
"metadata": {
"id": "xYfl52w6k6ZW"
}
},
{
"cell_type": "code",
"source": [
"process_all_mp3()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "XW4oyHCYmSuD",
"outputId": "0a3c717d-dfce-4206-9300-315a10e3fe6b"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"100%|██████████| 1/1 [33:09<00:00, 1989.32s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" TSV saved to: /content/drive/MyDrive/DP_data/adpocia3.tsv\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
}
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |