Overview

We present a CLSRIL-23 (Cross Lingual Speech Representations on Indic Languages), a self supervised learning based audio pre-trained model which learns cross lingual speech representations from raw audio across 23 Indic languages . It is built on top of wav2vec 2.0 which is solved by training a contrastive task over masked latent speech representations and jointly learns the quantization of latents shared across all languages.

Arxiv Link

Original Repo contains models in fairseq format.

Languages in the pretraining dataset

Repo for training:

Experimentation platform built on top of fairseq.