The MMS project has developed a single multilingual speech recognition model supporting over 1,100 languages, as well as language identification models able to identify over 4,000 languages and text-to-speech models for over 1,100 languages. These tools aim to make it easier for people to access information and use devices in their preferred language. The project also offers pretrained models for fine-tuning, as well as a forced alignment algorithm and multilingual alignment model. The MMS code and model weights are released under the CC-BY-NC 4.0 license.
https://github.com/facebookresearch/fairseq/tree/main/examples/mms