Multilingual discrete speech tokenizer for LLM.
-
mesolitica/whisper-conv-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 62 -
mesolitica/whisper-conv-VQ-32k-large-v3-turbo
Automatic Speech Recognition • 0.9B • Updated • 24 -
mesolitica/gemma3n-audio-encoder-whisper-decoder
Feature Extraction • 0.9B • Updated • 312 -
mesolitica/gemma3n-audio-encoder-VQ-32k-whisper-decoder
Feature Extraction • 0.9B • Updated • 36