mms

Massively Multilingual Speech (MMS) - Common Crawl Language Models

This repository consists of the n-gram language models trained on Common Crawl data (Conneau et al. 2020b, NLLB_Team et al. 2022) using KenLM library.

For the following languages, the LMs are not present in the repository (due to 50GB limit on HuggingFace) and can be downloaded using the link provided here.

Mandarin Chinese (Simplified) - Download LM

Japanese - Download LM

Thai - Download LM

Cantonese(Traditional) - Download LM

Table Of Content

Example

Checkout the code here - https://huggingface.co/spaces/mms-meta/MMS/blob/main/asr.py which uses LMs for decoding the output from ASR models.

Supported Languages

We support language models in 102 languages. Unclick the following to toogle all supported languages of this checkpoint in ISO 639-3 code. You can find more details about the languages and their ISO 639-3 codes in the MMS Language Coverage Overview.

Click to toggle
  • afr
  • amh
  • ara
  • asm
  • ast
  • azj
  • bel
  • ben
  • bos
  • bul
  • cat
  • ceb
  • ces
  • ckb
  • cmn
  • cym
  • dan
  • deu
  • ell
  • eng
  • est
  • fas
  • fin
  • fra
  • ful
  • gle
  • glg
  • guj
  • hau
  • heb
  • hin
  • hrv
  • hun
  • hye
  • ibo
  • ind
  • isl
  • ita
  • jav
  • jpn
  • kam
  • kan
  • kat
  • kaz
  • kea
  • khm
  • kir
  • kor
  • lao
  • lav
  • lin
  • lit
  • ltz
  • lug
  • luo
  • mal
  • mar
  • mkd
  • mlt
  • mon
  • mri
  • mya
  • nld
  • nob
  • npi
  • nso
  • nya
  • oci
  • orm
  • ory
  • pan
  • pol
  • por
  • pus
  • ron
  • rus
  • slk
  • slv
  • sna
  • snd
  • som
  • spa
  • srp
  • swe
  • swh
  • tam
  • tel
  • tgk
  • tgl
  • tha
  • tur
  • ukr
  • umb
  • urd
  • uzb
  • vie
  • wol
  • xho
  • yor
  • yue
  • zlm
  • zul

Model details

  • Developed by: Vineel Pratap et al.

  • Model type: Multi-Lingual Automatic Speech Recognition model

  • Language(s): 126 languages, see supported languages

  • License: CC-BY-NC 4.0 license

  • Num parameters: 1 billion

  • Audio sampling rate: 16,000 kHz

  • Cite as:

    @article{pratap2023mms,
      title={Scaling Speech Technology to 1,000+ Languages},
      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},
    journal={arXiv},
    year={2023}
    }
    

Additional Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Spaces using facebook/mms-cclms 27