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 Speech to text 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. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
Meta builds and maintains Mms Lid 256, and it first shipped in 2018. Development happens publicly on GitHub with 162.8k stars and 744 commits in the last 90 days.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do