README.md
| 1 | --- |
| 2 | tags: |
| 3 | - mms |
| 4 | language: |
| 5 | - ab |
| 6 | - af |
| 7 | - ak |
| 8 | - am |
| 9 | - ar |
| 10 | - as |
| 11 | - av |
| 12 | - ay |
| 13 | - az |
| 14 | - ba |
| 15 | - bm |
| 16 | - be |
| 17 | - bn |
| 18 | - bi |
| 19 | - bo |
| 20 | - sh |
| 21 | - br |
| 22 | - bg |
| 23 | - ca |
| 24 | - cs |
| 25 | - ce |
| 26 | - cv |
| 27 | - ku |
| 28 | - cy |
| 29 | - da |
| 30 | - de |
| 31 | - dv |
| 32 | - dz |
| 33 | - el |
| 34 | - en |
| 35 | - eo |
| 36 | - et |
| 37 | - eu |
| 38 | - ee |
| 39 | - fo |
| 40 | - fa |
| 41 | - fj |
| 42 | - fi |
| 43 | - fr |
| 44 | - fy |
| 45 | - ff |
| 46 | - ga |
| 47 | - gl |
| 48 | - gn |
| 49 | - gu |
| 50 | - zh |
| 51 | - ht |
| 52 | - ha |
| 53 | - he |
| 54 | - hi |
| 55 | - sh |
| 56 | - hu |
| 57 | - hy |
| 58 | - ig |
| 59 | - ia |
| 60 | - ms |
| 61 | - is |
| 62 | - it |
| 63 | - jv |
| 64 | - ja |
| 65 | - kn |
| 66 | - ka |
| 67 | - kk |
| 68 | - kr |
| 69 | - km |
| 70 | - ki |
| 71 | - rw |
| 72 | - ky |
| 73 | - ko |
| 74 | - kv |
| 75 | - lo |
| 76 | - la |
| 77 | - lv |
| 78 | - ln |
| 79 | - lt |
| 80 | - lb |
| 81 | - lg |
| 82 | - mh |
| 83 | - ml |
| 84 | - mr |
| 85 | - ms |
| 86 | - mk |
| 87 | - mg |
| 88 | - mt |
| 89 | - mn |
| 90 | - mi |
| 91 | - my |
| 92 | - zh |
| 93 | - nl |
| 94 | - 'no' |
| 95 | - 'no' |
| 96 | - ne |
| 97 | - ny |
| 98 | - oc |
| 99 | - om |
| 100 | - or |
| 101 | - os |
| 102 | - pa |
| 103 | - pl |
| 104 | - pt |
| 105 | - ms |
| 106 | - ps |
| 107 | - qu |
| 108 | - qu |
| 109 | - qu |
| 110 | - qu |
| 111 | - qu |
| 112 | - qu |
| 113 | - qu |
| 114 | - qu |
| 115 | - qu |
| 116 | - qu |
| 117 | - qu |
| 118 | - qu |
| 119 | - qu |
| 120 | - qu |
| 121 | - qu |
| 122 | - qu |
| 123 | - qu |
| 124 | - qu |
| 125 | - qu |
| 126 | - qu |
| 127 | - qu |
| 128 | - qu |
| 129 | - ro |
| 130 | - rn |
| 131 | - ru |
| 132 | - sg |
| 133 | - sk |
| 134 | - sl |
| 135 | - sm |
| 136 | - sn |
| 137 | - sd |
| 138 | - so |
| 139 | - es |
| 140 | - sq |
| 141 | - su |
| 142 | - sv |
| 143 | - sw |
| 144 | - ta |
| 145 | - tt |
| 146 | - te |
| 147 | - tg |
| 148 | - tl |
| 149 | - th |
| 150 | - ti |
| 151 | - ts |
| 152 | - tr |
| 153 | - uk |
| 154 | - ms |
| 155 | - vi |
| 156 | - wo |
| 157 | - xh |
| 158 | - ms |
| 159 | - yo |
| 160 | - ms |
| 161 | - zu |
| 162 | - za |
| 163 | license: cc-by-nc-4.0 |
| 164 | datasets: |
| 165 | - google/fleurs |
| 166 | metrics: |
| 167 | - acc |
| 168 | --- |
| 169 | |
| 170 | # Massively Multilingual Speech (MMS) - Finetuned LID |
| 171 | |
| 172 | This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's [Massive Multilingual Speech project](https://research.facebook.com/publications/scaling-speech-technology-to-1000-languages/). |
| 173 | This checkpoint is based on the [Wav2Vec2 architecture](https://huggingface.co/docs/transformers/model_doc/wav2vec2) and classifies raw audio input to a probability distribution over 1024 output classes (each class representing a language). |
| 174 | The checkpoint consists of **1 billion parameters** and has been fine-tuned from [facebook/mms-1b](https://huggingface.co/facebook/mms-1b) on 1024 languages. |
| 175 | |
| 176 | ## Table Of Content |
| 177 | |
| 178 | - [Example](#example) |
| 179 | - [Supported Languages](#supported-languages) |
| 180 | - [Model details](#model-details) |
| 181 | - [Additional links](#additional-links) |
| 182 | |
| 183 | ## Example |
| 184 | |
| 185 | This MMS checkpoint can be used with [Transformers](https://github.com/huggingface/transformers) to identify |
| 186 | the spoken language of an audio. It can recognize the [following 1024 languages](#supported-languages). |
| 187 | |
| 188 | Let's look at a simple example. |
| 189 | |
| 190 | First, we install transformers and some other libraries |
| 191 | ``` |
| 192 | pip install torch accelerate torchaudio datasets |
| 193 | pip install --upgrade transformers |
| 194 | ```` |
| 195 | |
| 196 | **Note**: In order to use MMS you need to have at least `transformers >= 4.30` installed. If the `4.30` version |
| 197 | is not yet available [on PyPI](https://pypi.org/project/transformers/) make sure to install `transformers` from |
| 198 | source: |
| 199 | ``` |
| 200 | pip install git+https://github.com/huggingface/transformers.git |
| 201 | ``` |
| 202 | |
| 203 | Next, we load a couple of audio samples via `datasets`. Make sure that the audio data is sampled to 16000 kHz. |
| 204 | |
| 205 | ```py |
| 206 | from datasets import load_dataset, Audio |
| 207 | |
| 208 | # English |
| 209 | stream_data = load_dataset("mozilla-foundation/common_voice_13_0", "en", split="test", streaming=True) |
| 210 | stream_data = stream_data.cast_column("audio", Audio(sampling_rate=16000)) |
| 211 | en_sample = next(iter(stream_data))["audio"]["array"] |
| 212 | |
| 213 | # Arabic |
| 214 | stream_data = load_dataset("mozilla-foundation/common_voice_13_0", "ar", split="test", streaming=True) |
| 215 | stream_data = stream_data.cast_column("audio", Audio(sampling_rate=16000)) |
| 216 | ar_sample = next(iter(stream_data))["audio"]["array"] |
| 217 | ``` |
| 218 | |
| 219 | Next, we load the model and processor |
| 220 | |
| 221 | ```py |
| 222 | from transformers import Wav2Vec2ForSequenceClassification, AutoFeatureExtractor |
| 223 | import torch |
| 224 | |
| 225 | model_id = "facebook/mms-lid-1024" |
| 226 | |
| 227 | processor = AutoFeatureExtractor.from_pretrained(model_id) |
| 228 | model = Wav2Vec2ForSequenceClassification.from_pretrained(model_id) |
| 229 | ``` |
| 230 | |
| 231 | Now we process the audio data, pass the processed audio data to the model to classify it into a language, just like we usually do for Wav2Vec2 audio classification models such as [ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition](https://huggingface.co/harshit345/xlsr-wav2vec-speech-emotion-recognition) |
| 232 | |
| 233 | ```py |
| 234 | # English |
| 235 | inputs = processor(en_sample, sampling_rate=16_000, return_tensors="pt") |
| 236 | |
| 237 | with torch.no_grad(): |
| 238 | outputs = model(**inputs).logits |
| 239 | |
| 240 | lang_id = torch.argmax(outputs, dim=-1)[0].item() |
| 241 | detected_lang = model.config.id2label[lang_id] |
| 242 | # 'eng' |
| 243 | |
| 244 | # Arabic |
| 245 | inputs = processor(ar_sample, sampling_rate=16_000, return_tensors="pt") |
| 246 | |
| 247 | with torch.no_grad(): |
| 248 | outputs = model(**inputs).logits |
| 249 | |
| 250 | lang_id = torch.argmax(outputs, dim=-1)[0].item() |
| 251 | detected_lang = model.config.id2label[lang_id] |
| 252 | # 'ara' |
| 253 | ``` |
| 254 | |
| 255 | To see all the supported languages of a checkpoint, you can print out the language ids as follows: |
| 256 | ```py |
| 257 | processor.id2label.values() |
| 258 | ``` |
| 259 | |
| 260 | For more details, about the architecture please have a look at [the official docs](https://huggingface.co/docs/transformers/main/en/model_doc/mms). |
| 261 | |
| 262 | ## Supported Languages |
| 263 | |
| 264 | This model supports 1024 languages. Unclick the following to toogle all supported languages of this checkpoint in [ISO 639-3 code](https://en.wikipedia.org/wiki/ISO_639-3). |
| 265 | You can find more details about the languages and their ISO 649-3 codes in the [MMS Language Coverage Overview](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html). |
| 266 | <details> |
| 267 | <summary>Click to toggle</summary> |
| 268 | |
| 269 | - ara |
| 270 | - cmn |
| 271 | - eng |
| 272 | - spa |
| 273 | - fra |
| 274 | - mlg |
| 275 | - swe |
| 276 | - por |
| 277 | - vie |
| 278 | - ful |
| 279 | - sun |
| 280 | - asm |
| 281 | - ben |
| 282 | - zlm |
| 283 | - kor |
| 284 | - ind |
| 285 | - hin |
| 286 | - tuk |
| 287 | - urd |
| 288 | - aze |
| 289 | - slv |
| 290 | - mon |
| 291 | - hau |
| 292 | - tel |
| 293 | - swh |
| 294 | - bod |
| 295 | - rus |
| 296 | - tur |
| 297 | - heb |
| 298 | - mar |
| 299 | - som |
| 300 | - tgl |
| 301 | - tat |
| 302 | - tha |
| 303 | - cat |
| 304 | - ron |
| 305 | - mal |
| 306 | - bel |
| 307 | - pol |
| 308 | - yor |
| 309 | - nld |
| 310 | - bul |
| 311 | - hat |
| 312 | - afr |
| 313 | - isl |
| 314 | - amh |
| 315 | - tam |
| 316 | - hun |
| 317 | - hrv |
| 318 | - lit |
| 319 | - cym |
| 320 | - fas |
| 321 | - mkd |
| 322 | - ell |
| 323 | - bos |
| 324 | - deu |
| 325 | - sqi |
| 326 | - jav |
| 327 | - kmr |
| 328 | - nob |
| 329 | - uzb |
| 330 | - snd |
| 331 | - lat |
| 332 | - nya |
| 333 | - grn |
| 334 | - mya |
| 335 | - orm |
| 336 | - lin |
| 337 | - hye |
| 338 | - yue |
| 339 | - pan |
| 340 | - jpn |
| 341 | - kaz |
| 342 | - npi |
| 343 | - kik |
| 344 | - kat |
| 345 | - guj |
| 346 | - kan |
| 347 | - tgk |
| 348 | - ukr |
| 349 | - ces |
| 350 | - lav |
| 351 | - bak |
| 352 | - khm |
| 353 | - cak |
| 354 | - fao |
| 355 | - glg |
| 356 | - ltz |
| 357 | - xog |
| 358 | - lao |
| 359 | - mlt |
| 360 | - sin |
| 361 | - aka |
| 362 | - sna |
| 363 | - che |
| 364 | - mam |
| 365 | - ita |
| 366 | - quc |
| 367 | - aiw |
| 368 | - srp |
| 369 | - mri |
| 370 | - tuv |
| 371 | - nno |
| 372 | - pus |
| 373 | - eus |
| 374 | - kbp |
| 375 | - gur |
| 376 | - ory |
| 377 | - lug |
| 378 | - crh |
| 379 | - bre |
| 380 | - luo |
| 381 | - nhx |
| 382 | - slk |
| 383 | - ewe |
| 384 | - xsm |
| 385 | - fin |
| 386 | - rif |
| 387 | - dan |
| 388 | - saq |
| 389 | - yid |
| 390 | - yao |
| 391 | - mos |
| 392 | - quh |
| 393 | - hne |
| 394 | - xon |
| 395 | - new |
| 396 | - dtp |
| 397 | - quy |
| 398 | - est |
| 399 | - ddn |
| 400 | - dyu |
| 401 | - ttq |
| 402 | - bam |
| 403 | - pse |
| 404 | - uig |
| 405 | - sck |
| 406 | - ngl |
| 407 | - tso |
| 408 | - mup |
| 409 | - dga |
| 410 | - seh |
| 411 | - lis |
| 412 | - wal |
| 413 | - ctg |
| 414 | - mip |
| 415 | - bfz |
| 416 | - bxk |
| 417 | - ceb |
| 418 | - kru |
| 419 | - war |
| 420 | - khg |
| 421 | - bbc |
| 422 | - thl |
| 423 | - nzi |
| 424 | - vmw |
| 425 | - mzi |
| 426 | - ycl |
| 427 | - zne |
| 428 | - sid |
| 429 | - asa |
| 430 | - tpi |
| 431 | - bmq |
| 432 | - box |
| 433 | - zpu |
| 434 | - gof |
| 435 | - nym |
| 436 | - cla |
| 437 | - bgq |
| 438 | - bfy |
| 439 | - hlb |
| 440 | - qxl |
| 441 | - teo |
| 442 | - fon |
| 443 | - sda |
| 444 | - kfx |
| 445 | - bfa |
| 446 | - mag |
| 447 | - tzh |
| 448 | - pil |
| 449 | - maj |
| 450 | - maa |
| 451 | - kdt |
| 452 | - ksb |
| 453 | - lns |
| 454 | - btd |
| 455 | - rej |
| 456 | - pap |
| 457 | - ayr |
| 458 | - any |
| 459 | - mnk |
| 460 | - adx |
| 461 | - gud |
| 462 | - krc |
| 463 | - onb |
| 464 | - xal |
| 465 | - ctd |
| 466 | - nxq |
| 467 | - ava |
| 468 | - blt |
| 469 | - lbw |
| 470 | - hyw |
| 471 | - udm |
| 472 | - zar |
| 473 | - tzo |
| 474 | - kpv |
| 475 | - san |
| 476 | - xnj |
| 477 | - kek |
| 478 | - chv |
| 479 | - kcg |
| 480 | - kri |
| 481 | - ati |
| 482 | - bgw |
| 483 | - mxt |
| 484 | - ybb |
| 485 | - btx |
| 486 | - dgi |
| 487 | - nhy |
| 488 | - dnj |
| 489 | - zpz |
| 490 | - yba |
| 491 | - lon |
| 492 | - smo |
| 493 | - men |
| 494 | - ium |
| 495 | - mgd |
| 496 | - taq |
| 497 | - nga |
| 498 | - nsu |
| 499 | - zaj |
| 500 | - tly |
| 501 | - prk |
| 502 | - zpt |
| 503 | - akb |
| 504 | - mhr |
| 505 | - mxb |
| 506 | - nuj |
| 507 | - obo |
| 508 | - kir |
| 509 | - bom |
| 510 | - run |
| 511 | - zpg |
| 512 | - hwc |
| 513 | - mnw |
| 514 | - ubl |
| 515 | - kin |
| 516 | - xtm |
| 517 | - hnj |
| 518 | - mpm |
| 519 | - rkt |
| 520 | - miy |
| 521 | - luc |
| 522 | - mih |
| 523 | - kne |
| 524 | - mib |
| 525 | - flr |
| 526 | - myv |
| 527 | - xmm |
| 528 | - knk |
| 529 | - iba |
| 530 | - gux |
| 531 | - pis |
| 532 | - zmz |
| 533 | - ses |
| 534 | - dav |
| 535 | - lif |
| 536 | - qxr |
| 537 | - dig |
| 538 | - kdj |
| 539 | - wsg |
| 540 | - tir |
| 541 | - gbm |
| 542 | - mai |
| 543 | - zpc |
| 544 | - kus |
| 545 | - nyy |
| 546 | - mim |
| 547 | - nan |
| 548 | - nyn |
| 549 | - gog |
| 550 | - ngu |
| 551 | - tbz |
| 552 | - hoc |
| 553 | - nyf |
| 554 | - sus |
| 555 | - guk |
| 556 | - gwr |
| 557 | - yaz |
| 558 | - bcc |
| 559 | - sbd |
| 560 | - spp |
| 561 | - hak |
| 562 | - grt |
| 563 | - kno |
| 564 | - oss |
| 565 | - suk |
| 566 | - spy |
| 567 | - nij |
| 568 | - lsm |
| 569 | - kaa |
| 570 | - bem |
| 571 | - rmy |
| 572 | - kqn |
| 573 | - nim |
| 574 | - ztq |
| 575 | - nus |
| 576 | - bib |
| 577 | - xtd |
| 578 | - ach |
| 579 | - mil |
| 580 | - keo |
| 581 | - mpg |
| 582 | - gjn |
| 583 | - zaq |
| 584 | - kdh |
| 585 | - dug |
| 586 | - sah |
| 587 | - awa |
| 588 | - kff |
| 589 | - dip |
| 590 | - rim |
| 591 | - nhe |
| 592 | - pcm |
| 593 | - kde |
| 594 | - tem |
| 595 | - quz |
| 596 | - mfq |
| 597 | - las |
| 598 | - bba |
| 599 | - kbr |
| 600 | - taj |
| 601 | - dyo |
| 602 | - zao |
| 603 | - lom |
| 604 | - shk |
| 605 | - dik |
| 606 | - dgo |
| 607 | - zpo |
| 608 | - fij |
| 609 | - bgc |
| 610 | - xnr |
| 611 | - bud |
| 612 | - kac |
| 613 | - laj |
| 614 | - mev |
| 615 | - maw |
| 616 | - quw |
| 617 | - kao |
| 618 | - dag |
| 619 | - ktb |
| 620 | - lhu |
| 621 | - zab |
| 622 | - mgh |
| 623 | - shn |
| 624 | - otq |
| 625 | - lob |
| 626 | - pbb |
| 627 | - oci |
| 628 | - zyb |
| 629 | - bsq |
| 630 | - mhi |
| 631 | - dzo |
| 632 | - zas |
| 633 | - guc |
| 634 | - alz |
| 635 | - ctu |
| 636 | - wol |
| 637 | - guw |
| 638 | - mnb |
| 639 | - nia |
| 640 | - zaw |
| 641 | - mxv |
| 642 | - bci |
| 643 | - sba |
| 644 | - kab |
| 645 | - dwr |
| 646 | - nnb |
| 647 | - ilo |
| 648 | - mfe |
| 649 | - srx |
| 650 | - ruf |
| 651 | - srn |
| 652 | - zad |
| 653 | - xpe |
| 654 | - pce |
| 655 | - ahk |
| 656 | - bcl |
| 657 | - myk |
| 658 | - haw |
| 659 | - mad |
| 660 | - ljp |
| 661 | - bky |
| 662 | - gmv |
| 663 | - nag |
| 664 | - nav |
| 665 | - nyo |
| 666 | - kxm |
| 667 | - nod |
| 668 | - sag |
| 669 | - zpl |
| 670 | - sas |
| 671 | - myx |
| 672 | - sgw |
| 673 | - old |
| 674 | - irk |
| 675 | - acf |
| 676 | - mak |
| 677 | - kfy |
| 678 | - zai |
| 679 | - mie |
| 680 | - zpm |
| 681 | - zpi |
| 682 | - ote |
| 683 | - jam |
| 684 | - kpz |
| 685 | - lgg |
| 686 | - lia |
| 687 | - nhi |
| 688 | - mzm |
| 689 | - bdq |
| 690 | - xtn |
| 691 | - mey |
| 692 | - mjl |
| 693 | - sgj |
| 694 | - kdi |
| 695 | - kxc |
| 696 | - miz |
| 697 | - adh |
| 698 | - tap |
| 699 | - hay |
| 700 | - kss |
| 701 | - pam |
| 702 | - gor |
| 703 | - heh |
| 704 | - nhw |
| 705 | - ziw |
| 706 | - gej |
| 707 | - yua |
| 708 | - itv |
| 709 | - shi |
| 710 | - qvw |
| 711 | - mrw |
| 712 | - hil |
| 713 | - mbt |
| 714 | - pag |
| 715 | - vmy |
| 716 | - lwo |
| 717 | - cce |
| 718 | - kum |
| 719 | - klu |
| 720 | - ann |
| 721 | - mbb |
| 722 | - npl |
| 723 | - zca |
| 724 | - pww |
| 725 | - toc |
| 726 | - ace |
| 727 | - mio |
| 728 | - izz |
| 729 | - kam |
| 730 | - zaa |
| 731 | - krj |
| 732 | - bts |
| 733 | - eza |
| 734 | - zty |
| 735 | - hns |
| 736 | - kki |
| 737 | - min |
| 738 | - led |
| 739 | - alw |
| 740 | - tll |
| 741 | - rng |
| 742 | - pko |
| 743 | - toi |
| 744 | - iqw |
| 745 | - ncj |
| 746 | - toh |
| 747 | - umb |
| 748 | - mog |
| 749 | - hno |
| 750 | - wob |
| 751 | - gxx |
| 752 | - hig |
| 753 | - nyu |
| 754 | - kby |
| 755 | - ban |
| 756 | - syl |
| 757 | - bxg |
| 758 | - nse |
| 759 | - xho |
| 760 | - zae |
| 761 | - mkw |
| 762 | - nch |
| 763 | - ibg |
| 764 | - mas |
| 765 | - qvz |
| 766 | - bum |
| 767 | - bgd |
| 768 | - mww |
| 769 | - epo |
| 770 | - tzm |
| 771 | - zul |
| 772 | - bcq |
| 773 | - lrc |
| 774 | - xdy |
| 775 | - tyv |
| 776 | - ibo |
| 777 | - loz |
| 778 | - mza |
| 779 | - abk |
| 780 | - azz |
| 781 | - guz |
| 782 | - arn |
| 783 | - ksw |
| 784 | - lus |
| 785 | - tos |
| 786 | - gvr |
| 787 | - top |
| 788 | - ckb |
| 789 | - mer |
| 790 | - pov |
| 791 | - lun |
| 792 | - rhg |
| 793 | - knc |
| 794 | - sfw |
| 795 | - bev |
| 796 | - tum |
| 797 | - lag |
| 798 | - nso |
| 799 | - bho |
| 800 | - ndc |
| 801 | - maf |
| 802 | - gkp |
| 803 | - bax |
| 804 | - awn |
| 805 | - ijc |
| 806 | - qug |
| 807 | - lub |
| 808 | - srr |
| 809 | - mni |
| 810 | - zza |
| 811 | - ige |
| 812 | - dje |
| 813 | - mkn |
| 814 | - bft |
| 815 | - tiv |
| 816 | - otn |
| 817 | - kck |
| 818 | - kqs |
| 819 | - gle |
| 820 | - lua |
| 821 | - pdt |
| 822 | - swk |
| 823 | - mgw |
| 824 | - ebu |
| 825 | - ada |
| 826 | - lic |
| 827 | - skr |
| 828 | - gaa |
| 829 | - mfa |
| 830 | - vmk |
| 831 | - mcn |
| 832 | - bto |
| 833 | - lol |
| 834 | - bwr |
| 835 | - unr |
| 836 | - dzg |
| 837 | - hdy |
| 838 | - kea |
| 839 | - bhi |
| 840 | - glk |
| 841 | - mua |
| 842 | - ast |
| 843 | - nup |
| 844 | - sat |
| 845 | - ktu |
| 846 | - bhb |
| 847 | - zpq |
| 848 | - coh |
| 849 | - bkm |
| 850 | - gya |
| 851 | - sgc |
| 852 | - dks |
| 853 | - ncl |
| 854 | - tui |
| 855 | - emk |
| 856 | - urh |
| 857 | - ego |
| 858 | - ogo |
| 859 | - tsc |
| 860 | - idu |
| 861 | - igb |
| 862 | - ijn |
| 863 | - njz |
| 864 | - ngb |
| 865 | - tod |
| 866 | - jra |
| 867 | - mrt |
| 868 | - zav |
| 869 | - tke |
| 870 | - its |
| 871 | - ady |
| 872 | - bzw |
| 873 | - kng |
| 874 | - kmb |
| 875 | - lue |
| 876 | - jmx |
| 877 | - tsn |
| 878 | - bin |
| 879 | - ble |
| 880 | - gom |
| 881 | - ven |
| 882 | - sef |
| 883 | - sco |
| 884 | - her |
| 885 | - iso |
| 886 | - trp |
| 887 | - glv |
| 888 | - haq |
| 889 | - toq |
| 890 | - okr |
| 891 | - kha |
| 892 | - wof |
| 893 | - rmn |
| 894 | - sot |
| 895 | - kaj |
| 896 | - bbj |
| 897 | - sou |
| 898 | - mjt |
| 899 | - trd |
| 900 | - gno |
| 901 | - mwn |
| 902 | - igl |
| 903 | - rag |
| 904 | - eyo |
| 905 | - div |
| 906 | - efi |
| 907 | - nde |
| 908 | - mfv |
| 909 | - mix |
| 910 | - rki |
| 911 | - kjg |
| 912 | - fan |
| 913 | - khw |
| 914 | - wci |
| 915 | - bjn |
| 916 | - pmy |
| 917 | - bqi |
| 918 | - ina |
| 919 | - hni |
| 920 | - mjx |
| 921 | - kuj |
| 922 | - aoz |
| 923 | - the |
| 924 | - tog |
| 925 | - tet |
| 926 | - nuz |
| 927 | - ajg |
| 928 | - ccp |
| 929 | - mau |
| 930 | - ymm |
| 931 | - fmu |
| 932 | - tcz |
| 933 | - xmc |
| 934 | - nyk |
| 935 | - ztg |
| 936 | - knx |
| 937 | - snk |
| 938 | - zac |
| 939 | - esg |
| 940 | - srb |
| 941 | - thq |
| 942 | - pht |
| 943 | - wes |
| 944 | - rah |
| 945 | - pnb |
| 946 | - ssy |
| 947 | - zpv |
| 948 | - kpo |
| 949 | - phr |
| 950 | - atd |
| 951 | - eto |
| 952 | - xta |
| 953 | - mxx |
| 954 | - mui |
| 955 | - uki |
| 956 | - tkt |
| 957 | - mgp |
| 958 | - xsq |
| 959 | - enq |
| 960 | - nnh |
| 961 | - qxp |
| 962 | - zam |
| 963 | - bug |
| 964 | - bxr |
| 965 | - maq |
| 966 | - tdt |
| 967 | - khb |
| 968 | - mrr |
| 969 | - kas |
| 970 | - zgb |
| 971 | - kmw |
| 972 | - lir |
| 973 | - vah |
| 974 | - dar |
| 975 | - ssw |
| 976 | - hmd |
| 977 | - jab |
| 978 | - iii |
| 979 | - peg |
| 980 | - shr |
| 981 | - brx |
| 982 | - rwr |
| 983 | - bmb |
| 984 | - kmc |
| 985 | - mji |
| 986 | - dib |
| 987 | - pcc |
| 988 | - nbe |
| 989 | - mrd |
| 990 | - ish |
| 991 | - kai |
| 992 | - yom |
| 993 | - zyn |
| 994 | - hea |
| 995 | - ewo |
| 996 | - bas |
| 997 | - hms |
| 998 | - twh |
| 999 | - kfq |
| 1000 | - thr |
| 1001 | - xtl |
| 1002 | - wbr |
| 1003 | - bfb |
| 1004 | - wtm |
| 1005 | - mjc |
| 1006 | - blk |
| 1007 | - lot |
| 1008 | - dhd |
| 1009 | - swv |
| 1010 | - wbm |
| 1011 | - zzj |
| 1012 | - kge |
| 1013 | - mgm |
| 1014 | - niq |
| 1015 | - zpj |
| 1016 | - bwx |
| 1017 | - bde |
| 1018 | - mtr |
| 1019 | - gju |
| 1020 | - kjp |
| 1021 | - mbz |
| 1022 | - haz |
| 1023 | - lpo |
| 1024 | - yig |
| 1025 | - qud |
| 1026 | - shy |
| 1027 | - gjk |
| 1028 | - ztp |
| 1029 | - nbl |
| 1030 | - aii |
| 1031 | - kun |
| 1032 | - say |
| 1033 | - mde |
| 1034 | - sjp |
| 1035 | - bns |
| 1036 | - brh |
| 1037 | - ywq |
| 1038 | - msi |
| 1039 | - anr |
| 1040 | - mrg |
| 1041 | - mjg |
| 1042 | - tan |
| 1043 | - tsg |
| 1044 | - tcy |
| 1045 | - kbl |
| 1046 | - mdr |
| 1047 | - mks |
| 1048 | - noe |
| 1049 | - tyz |
| 1050 | - zpa |
| 1051 | - ahr |
| 1052 | - aar |
| 1053 | - wuu |
| 1054 | - khr |
| 1055 | - kbd |
| 1056 | - kex |
| 1057 | - bca |
| 1058 | - nku |
| 1059 | - pwr |
| 1060 | - hsn |
| 1061 | - ort |
| 1062 | - ott |
| 1063 | - swi |
| 1064 | - kua |
| 1065 | - tdd |
| 1066 | - msm |
| 1067 | - bgp |
| 1068 | - nbm |
| 1069 | - mxy |
| 1070 | - abs |
| 1071 | - zlj |
| 1072 | - ebo |
| 1073 | - lea |
| 1074 | - dub |
| 1075 | - sce |
| 1076 | - xkb |
| 1077 | - vav |
| 1078 | - bra |
| 1079 | - ssb |
| 1080 | - sss |
| 1081 | - nhp |
| 1082 | - kad |
| 1083 | - kvx |
| 1084 | - lch |
| 1085 | - tts |
| 1086 | - zyj |
| 1087 | - kxp |
| 1088 | - lmn |
| 1089 | - qvi |
| 1090 | - lez |
| 1091 | - scl |
| 1092 | - cqd |
| 1093 | - ayb |
| 1094 | - xbr |
| 1095 | - nqg |
| 1096 | - dcc |
| 1097 | - cjk |
| 1098 | - bfr |
| 1099 | - zyg |
| 1100 | - mse |
| 1101 | - gru |
| 1102 | - mdv |
| 1103 | - bew |
| 1104 | - wti |
| 1105 | - arg |
| 1106 | - dso |
| 1107 | - zdj |
| 1108 | - pll |
| 1109 | - mig |
| 1110 | - qxs |
| 1111 | - bol |
| 1112 | - drs |
| 1113 | - anp |
| 1114 | - chw |
| 1115 | - bej |
| 1116 | - vmc |
| 1117 | - otx |
| 1118 | - xty |
| 1119 | - bjj |
| 1120 | - vmz |
| 1121 | - ibb |
| 1122 | - gby |
| 1123 | - twx |
| 1124 | - tig |
| 1125 | - thz |
| 1126 | - tku |
| 1127 | - hmz |
| 1128 | - pbm |
| 1129 | - mfn |
| 1130 | - nut |
| 1131 | - cyo |
| 1132 | - mjw |
| 1133 | - cjm |
| 1134 | - tlp |
| 1135 | - naq |
| 1136 | - rnd |
| 1137 | - stj |
| 1138 | - sym |
| 1139 | - jax |
| 1140 | - btg |
| 1141 | - tdg |
| 1142 | - sng |
| 1143 | - nlv |
| 1144 | - kvr |
| 1145 | - pch |
| 1146 | - fvr |
| 1147 | - mxs |
| 1148 | - wni |
| 1149 | - mlq |
| 1150 | - kfr |
| 1151 | - mdj |
| 1152 | - osi |
| 1153 | - nhn |
| 1154 | - ukw |
| 1155 | - tji |
| 1156 | - qvj |
| 1157 | - nih |
| 1158 | - bcy |
| 1159 | - hbb |
| 1160 | - zpx |
| 1161 | - hoj |
| 1162 | - cpx |
| 1163 | - ogc |
| 1164 | - cdo |
| 1165 | - bgn |
| 1166 | - bfs |
| 1167 | - vmx |
| 1168 | - tvn |
| 1169 | - ior |
| 1170 | - mxa |
| 1171 | - btm |
| 1172 | - anc |
| 1173 | - jit |
| 1174 | - mfb |
| 1175 | - mls |
| 1176 | - ets |
| 1177 | - goa |
| 1178 | - bet |
| 1179 | - ikw |
| 1180 | - pem |
| 1181 | - trf |
| 1182 | - daq |
| 1183 | - max |
| 1184 | - rad |
| 1185 | - njo |
| 1186 | - bnx |
| 1187 | - mxl |
| 1188 | - mbi |
| 1189 | - nba |
| 1190 | - zpn |
| 1191 | - zts |
| 1192 | - mut |
| 1193 | - hnd |
| 1194 | - mta |
| 1195 | - hav |
| 1196 | - hac |
| 1197 | - ryu |
| 1198 | - abr |
| 1199 | - yer |
| 1200 | - cld |
| 1201 | - zag |
| 1202 | - ndo |
| 1203 | - sop |
| 1204 | - vmm |
| 1205 | - gcf |
| 1206 | - chr |
| 1207 | - cbk |
| 1208 | - sbk |
| 1209 | - bhp |
| 1210 | - odk |
| 1211 | - mbd |
| 1212 | - nap |
| 1213 | - gbr |
| 1214 | - mii |
| 1215 | - czh |
| 1216 | - xti |
| 1217 | - vls |
| 1218 | - gdx |
| 1219 | - sxw |
| 1220 | - zaf |
| 1221 | - wem |
| 1222 | - mqh |
| 1223 | - ank |
| 1224 | - yaf |
| 1225 | - vmp |
| 1226 | - otm |
| 1227 | - sdh |
| 1228 | - anw |
| 1229 | - src |
| 1230 | - mne |
| 1231 | - wss |
| 1232 | - meh |
| 1233 | - kzc |
| 1234 | - tma |
| 1235 | - ttj |
| 1236 | - ots |
| 1237 | - ilp |
| 1238 | - zpr |
| 1239 | - saz |
| 1240 | - ogb |
| 1241 | - akl |
| 1242 | - nhg |
| 1243 | - pbv |
| 1244 | - rcf |
| 1245 | - cgg |
| 1246 | - mku |
| 1247 | - bez |
| 1248 | - mwe |
| 1249 | - mtb |
| 1250 | - gul |
| 1251 | - ifm |
| 1252 | - mdh |
| 1253 | - scn |
| 1254 | - lki |
| 1255 | - xmf |
| 1256 | - sgd |
| 1257 | - aba |
| 1258 | - cos |
| 1259 | - luz |
| 1260 | - zpy |
| 1261 | - stv |
| 1262 | - kjt |
| 1263 | - mbf |
| 1264 | - kmz |
| 1265 | - nds |
| 1266 | - mtq |
| 1267 | - tkq |
| 1268 | - aee |
| 1269 | - knn |
| 1270 | - mbs |
| 1271 | - mnp |
| 1272 | - ema |
| 1273 | - bar |
| 1274 | - unx |
| 1275 | - plk |
| 1276 | - psi |
| 1277 | - mzn |
| 1278 | - cja |
| 1279 | - sro |
| 1280 | - mdw |
| 1281 | - ndh |
| 1282 | - vmj |
| 1283 | - zpw |
| 1284 | - kfu |
| 1285 | - bgx |
| 1286 | - gsw |
| 1287 | - fry |
| 1288 | - zpe |
| 1289 | - zpd |
| 1290 | - bta |
| 1291 | - psh |
| 1292 | - zat |
| 1293 | |
| 1294 | </details> |
| 1295 | |
| 1296 | ## Model details |
| 1297 | |
| 1298 | - **Developed by:** Vineel Pratap et al. |
| 1299 | - **Model type:** Multi-Lingual Automatic Speech Recognition model |
| 1300 | - **Language(s):** 1024 languages, see [supported languages](#supported-languages) |
| 1301 | - **License:** CC-BY-NC 4.0 license |
| 1302 | - **Num parameters**: 1 billion |
| 1303 | - **Audio sampling rate**: 16,000 kHz |
| 1304 | - **Cite as:** |
| 1305 | |
| 1306 | @article{pratap2023mms, |
| 1307 | title={Scaling Speech Technology to 1,000+ Languages}, |
| 1308 | author={Vineel Pratap and Andros Tjandra and Bowen Shi and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam Fazel-Zarandi and Alexei Baevski and Yossi Adi and Xiaohui Zhang and Wei-Ning Hsu and Alexis Conneau and Michael Auli}, |
| 1309 | journal={arXiv}, |
| 1310 | year={2023} |
| 1311 | } |
| 1312 | |
| 1313 | ## Additional Links |
| 1314 | |
| 1315 | - [Blog post](https://ai.facebook.com/blog/multilingual-model-speech-recognition/) |
| 1316 | - [Transformers documentation](https://huggingface.co/docs/transformers/main/en/model_doc/mms). |
| 1317 | - [Paper](https://arxiv.org/abs/2305.13516) |
| 1318 | - [GitHub Repository](https://github.com/facebookresearch/fairseq/tree/main/examples/mms#asr) |
| 1319 | - [Other **MMS** checkpoints](https://huggingface.co/models?other=mms) |
| 1320 | - MMS base checkpoints: |
| 1321 | - [facebook/mms-1b](https://huggingface.co/facebook/mms-1b) |
| 1322 | - [facebook/mms-300m](https://huggingface.co/facebook/mms-300m) |
| 1323 | - [Official Space](https://huggingface.co/spaces/facebook/MMS) |
| 1324 | |