# Multitask Speech Processing

A speech-to-text large language model customized for Singapore's multilingual and multicultural environment, integrating Whisper-large-v2 speech encoder and SEA-LION V3 text decoder

Kotoba-Whisper-Bilingual is a distilled model collection trained from the Whisper model, specifically designed for Japanese and English speech recognition and speech-to-text translation tasks.

FunASR is a foundational toolkit dedicated to bridging academic research and industrial applications in speech recognition, supporting various functions such as speech recognition, voice activity detection, and punctuation restoration.