Xilinx / brevitas

Brevitas: neural network quantization in PyTorch

Home Page:https://xilinx.github.io/brevitas/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Speech to text: Create en empty json file

rohanjuneja opened this issue · comments

The command to download and preprocess the LibriSpeech dataset creates an empty json file.
brevitas_quartznet_preprocess --data_root=/path/to/validation/folder --data_set=DEV_OTHER

This causes the evaluation command to fail.

Thanks for pointing this out.
We will investigate the issue.

This should be fixed now. Thanks for opening the issue!