Search papers, labs, and topics across Lattice.
3
0
6
1
The architecture, training methodology and inference speedups of Granite 5.0 Turbo CTC result in a model that is on the speed-accuracy Pareto frontier of the Open ASR leaderboard for English short-form ASR while being twice as fast as the fastest competitor.
Forget phoneme sequences and G2P systems: this work shows you can boost ASR accuracy for rare words by cleverly leveraging acoustic cues from common words with similar sounds.
LLM-based ASR can be sped up by 4.4x with minimal accuracy loss by using a CTC encoder to speculatively generate draft transcriptions.