Facebook's mms-lid-256 is part of the Massively Multilingual Speech project. It performs audio classification to identify the language of spoken audio across 256 languages. The model is distributed on Hugging Face and can be used with Transformers for speech-related applications.
In the Voice, TTS & speech space, Mms Lid 256 takes a focused approach. It focuses on identifying spoken languages across 100+ languages from audio input. It is built as an open-source project for developers. Mms Lid 256 is open source under the Apache-2.0 license. The product ships for the web, the command line, and API.
Behind Mms Lid 256 is Meta, and the product first shipped in 2018. Development happens publicly on GitHub with 162.8k stars and 744 commits in the last 90 days.
Latest indexed changes and source events
facebook/mms-lid-256 verified by the PulseGate indexer
Other apps tracked under the same category.
