This is the repository of Visual Speech Recognition for Multiple Languages, which is the successor of End-to-End Audio-Visual Speech Recognition with Conformers. By using this repository, you can ...

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Using your contacts as a training tool can turn voice recognition from an occasional helper into a much more reliable productivity partner.

Voice recognition have gained much more popularity in recent times; though it has existed for more than a couple of decades, but it has regained popularity due to recent technological developments.

In a recent study, scientists successfully decoded not only the words people tried to say but the words they merely imagined saying.

The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the ...