LLM and ASR

Speech recognition on your laptop

by

Following on from the work reported on two posts ago with progress on speech recognition for Bislama and Nafsan, Aso Mahmudi has now created a desktop app (called Easper – Elan Automated Speech Recognition) that takes a wav file as input, segments it, does speaker diarisation, and transcribes it, delivering an Elan file as the … Read more

Email, RSS Follow

Large language models for small languages

by

Of the 7,000 languages in the world today, most have little presence on the internet. What records there are in these languages are often religious translations from large languages and so, while being a valuable set of texts in the language, they have little local cultural content. For some of these languages, there are recordings … Read more

Email, RSS Follow