NVIDIA
NVIDIA
STT By Conformer-RNNT Large
Model
NVIDIA
NVIDIA
STT By Conformer-RNNT Large

This collection contains the large version (114M) of the Belarusian speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.

NameSizeUpdatedActions
stt_by_fastconformer_hybrid_large_pc.nemo
437.98 MBMarch 1, 2025 UTC