Using BERT as the Language Model in Jarvis ASR

AI & Data Science Deep Learning (Training & Inference) Riva
1

Description

This is more of a question, so apologies if it’s out of context.
Is it possible to use the BERT model as the Language Model component of Jarvis ASR?

Environment

TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered
2 Likes
6

Hi @alifathi.bagh
Not sure if I understood you question correctly.
BERT is currently supported as part of Natural Processing (NLP). For ASR you can use Jasper or QuartzNet, please refer below link for more details:
https://docs.nvidia.com/deeplearning/jarvis/user-guide/docs/service-asr.html#model-architectures

Thanks