Automatic Speech Recognition
NeMo
Japanese
NeMo

Model training manner

#1
by hoangtm - opened

Hi ! First of all, thank you for you r great work. Can you tell me do you train your model in online or offline manner ? Thank you very much

develops models and technology like giving birth and then abandons it, no one to answer anything in here, should rather delete this project.

Reazon Human Interaction Lab org

This model is trained on Nvidia NeMo FastConformer CTC recipe. You can view the
training template in NeMo's examples/asr/conf/fastconformer directory:

https://github.com/NVIDIA/NeMo/tree/main/examples/asr/conf/fastconformer/long_fastconformer

The training process is the same as the other standard NeMo models. Nvidia publishes a
number of tutorials, so the best way to get started is pick one of them and follow it.

https://docs.nvidia.com/nemo-framework/user-guide/24.07/nemotoolkit/starthere/tutorials.html

online or offline manner

Offline.

fujimotos changed discussion status to closed

Sign up or log in to comment