Whisper Turbo
Software / AppMentioned in 1 video
A new, more efficient version of Whisper that uses model pruning (reducing decoder layers from 32 to 4) and continued pre-training. It is smaller and faster with minimal accuracy loss.
A new, more efficient version of Whisper that uses model pruning (reducing decoder layers from 32 to 4) and continued pre-training. It is smaller and faster with minimal accuracy loss.