search

NVIDIA / OpenSeq2Seq

Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
https://nvidia.github.io/OpenSeq2Seq
Apache License 2.0
1.54k stars 372 forks source link

Pass filename to get_speech_features() #491

Closed Shujian2015 closed 4 years ago

Shujian2015 commented 4 years ago

Pass filename to get_speech_features(). Otherwise, when the sample frequencies are not matched, it cannot find filename to display.

vsl9 commented 4 years ago

Thank you for the PR. The issue was fixed by checking for sample rate before calling get_speech_features.