Massively Multilingual Speech (MMS) - 1B

Facebook's MMS counting 1 billion parameters.

MMS is Facebook AI's massive multilingual pretrained model for speech ("MMS"). It is pretrained in with Wav2Vec2's self-supervised training objective on about 500,000 hours of speech data in over 1,400 languages.

When using the model make sure that your speech input is sampled at 16kHz.

Note : This model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Translation, or Classification. Check out the **How-to-fine section or this blog for more information about ASR.

Table Of Content

• How to Finetune
• Model details
• Additional links

How to finetune

Coming soon...

Model details

• Developed by: Vineel Pratap et al.

• Model type: Multi-Lingual Automatic Speech Recognition model

• Language(s): 1000+ languages

• License: CC-BY-NC 4.0 license

• Num parameters : 1 billion

• 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

• Blog post
• Transformers documentation .
• Paper
• GitHub Repository
• Other MMS checkpoints
• MMS ASR fine-tuned checkpoints:
  • facebook/mms-1b-all
  • facebook/mms-1b-l1107
  • facebook/mms-1b-fl102
• Official Space