清华大学 Speech and Audio Technology Lab--Home--Resource

Resource

Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages
GigaSpeech 2: 30,000-Hour Southeast Asian Multilingual Speech Recognition Open-Source Dataset
SpeechColab Leaderboard: An Open-Source Platform for Automatic Speech Recognition Evaluation
GigaSpeech: An Evolving, Multi-Domain ASR Corpus with 10,000 Hours of Transcribed Audio
NCMMSC2021-AD: NCMMSC2021 Alzheimer's Disease Recognition Evaluation Baseline and Dataset

total5 1/1

firstpreviousnextlast