Updated RNN-T input data size

mlcommons / inference_policies

Issues related to MLPerf™ Inference policies, including rules and suggested changes

https://mlcommons.org/en/groups/inference/

Apache License 2.0

55 stars 52 forks source link

Updated RNN-T input data size #234

Closed anirban-ghosh closed 2 years ago

anirban-ghosh commented 2 years ago

RNN-T input size was incorrect in the previous push. Corrected the input size per item to: 15 (sec) x 16 kHz x (16 bits/sample /8) = 480000 Bytes per example.

github-actions[bot] commented 2 years ago

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

nv-ananjappa commented 2 years ago

LGTM