enactic/avsr-leaderboard
Updated
•
10
AVista 🐦🔥
Toward a new vista of Human–Robot Interaction. AVista stands for Audio‑VIsual Speech Transcription & Alignment.
-
-
enactic/avista-large-plus-v2
Automatic Speech Recognition • Updated • 57 -
enactic/avista-large-v2
Automatic Speech Recognition • Updated • 46 -
enactic/avista-base-plus-v2
Automatic Speech Recognition • Updated • 20 -
enactic/avista-base-v2
Automatic Speech Recognition • Updated • 5 -
enactic/avista-large-plus
Automatic Speech Recognition • Updated • 2 -
enactic/avista-large
Automatic Speech Recognition • Updated • 5 -
enactic/avista-base-plus
Automatic Speech Recognition • Updated • 5 -
enactic/avista-base
Automatic Speech Recognition • Updated • 5 -
enactic/japanese-avhubert-large_noise_pt
Feature Extraction • 0.3B • Updated • 1 -
enactic/japanese-avhubert-large
Feature Extraction • 0.3B • Updated • 6 -
enactic/japanese-avhubert-base_noise_pt
Feature Extraction • 0.1B • Updated • 6 -
enactic/japanese-avhubert-base
Feature Extraction • 0.1B • Updated • 6 -
enactic/japanese-avhubert-base-penultimate
Feature Extraction • 0.1B • Updated • 5 -
enactic/japanese-avhubert-base-iter3
Feature Extraction • 0.1B • Updated • 5 -
enactic/japanese-avhubert-base-iter2
Feature Extraction • 0.1B • Updated • 3 -
enactic/japanese-avhubert-base-iter1
Feature Extraction • 0.1B • Updated • 7