Scaling Speech Technology to 1,000+ Languages

Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu +11 more
5/22/2023
cs.CLcs.SDeess.AS

No official code found. Best implementation: facebookresearch/fairseq (32,213 stars, MIT, PyTorch, last commit 2025-09-30).

Abstract

Expanding the language coverage of speech technology has the potential to improve access to information for many more people. However, current speech technology is restricted to about one hundred languages which is a small fraction of the over 7,000 languages spoken around the world. The Massively Multilingual Speech (MMS) project increases the number of supported languages by 10-40x, depending on the task. The main ingredients are a new dataset based on readings of publicly available religious texts and effectively leveraging self-supervised learning. We built pre-trained wav2vec 2.0 models covering 1,406 languages, a single multilingual automatic speech recognition model for 1,107 languages, speech synthesis models for the same number of languages, as well as a language identification model for 4,017 languages. Experiments show that our multilingual speech recognition model more than halves the word error rate of Whisper on 54 languages of the FLEURS benchmark while being trained on a small fraction of the labeled data.

View on arXivView PDF

Code Implementations(1)

facebookresearch/fairseqCommunity100%
PyTorchMIT

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

32,2136,667C++, LuaAug 29, 20171 years agoMIT
artificial-intelligencepythonpytorch

Similar Papers

BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models

89% match2026

Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning

89% match2022

Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

89% match2023

Monsoon: Scalable Spontaneous Speech Collection for Low-Resource ASR in 50 Languages

87% match2026

Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian Languages

86% match2026

Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR

86% match1 repo72026

Cite this paper

@article{pratap2023scaling,
  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},
  year   = {2023},
  eprint = {2305.13516},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.13516v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.13516.svg)](https://codeofpaper.com/paper/2305.13516)

Discussion