slprl/slam
Audio-to-Audio
•
0.4B
•
Updated
•
53
•
11
Slam
All resources for SpeechLMs from "Slamming: Training a Speech Language Model on One GPU in a Day". We provide tokeniser, lm, and datasets
-
-
slprl/slam_scaled
Audio-to-Audio • 0.4B • Updated • 174 • 6 -
slprl/SpokenSwag
Viewer • Updated • 67.9k • 328 • 4 -
slprl/mhubert-base-25hz
Feature Extraction • 0.1B • Updated • 3.57k • • 4 -
slprl/sTinyStories
Viewer • Updated • 1.88M • 6.46k • 6 -
Slamming: Training a Speech Language Model on One GPU in a Day
Paper • 2502.15814 • Published • 70 -
slprl/slam_large
Audio-to-Audio • 1B • Updated • 10 • 3