The SPEAR encoder models. Original version: https://arxiv.org/abs/2510.25955v1, and the updated version: https://arxiv.org/abs/2510.25955.
Xiaoyu Yang
marcoyang
AI & ML interests
ASR, Machine learning
Recent Activity
updated a model 1 day ago
marcoyang/spear-xlarge-speech-audio-v2-icefall published a model 1 day ago
marcoyang/spear-xlarge-speech-audio-v2-icefall updated a model about 2 months ago
marcoyang/spear-base-speech-audio-v2Organizations
models 49
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 92
marcoyang/spear-base-speech-v2
93.3M • Updated • 133
marcoyang/spear-base-speech-audio
93.3M • Updated • 6 • 2
marcoyang/spear-base-speech
93.3M • Updated • 38
marcoyang/spear-large-speech-audio
0.3B • Updated • 142
marcoyang/spear-large-speech
0.3B • Updated • 15
marcoyang/spear-xlarge-speech-audio
0.6B • Updated • 40.1k • 4
marcoyang/transformer-causal-600m-spear-speech
Updated
marcoyang/spear-xlarge-speech-audio-augmentation
Updated