Model
ASR Conformer en-US NeuralVAD enabled model
Sign in to access this content
NeuralVAD enabled RIVA Conformer ASR English model
This model is customized version of RIVA Conformer ASR English model with NeuralVAD enabled for voice activity. Conformer-CTC (around 120M parameters) is trained on ASRSet with over 35000 hours of English (en-US) speech. The model transcribes speech in lower case English alphabet along with spaces and apostrophes.
Documentation
License
By downloading and using this software, you accept the terms and conditions of this license.
Publisher
NVIDIA
Latest Version2.15.0-tokkio
UpdatedNovember 11, 2024 UTC
Compressed Size929.94 MB
Labels