mozilla/DeepSpeech

Replace LDC93S1 sample in prod tests with something else

Open

#2732 aperta il 10 feb 2020

Vedi su GitHub
 (1 commento) (0 reazioni) (0 assegnatari)C++ (4093 fork)batch import
good first bughelp wanted

Metriche repository

Star
 (26.755 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

LDC93S1 prod model outputs vary wildly across versions of the prod model and our inference runtime, because we don't train with anything like TIMIT, so predictions are not confident. We should use some sample from eg. LibriSpeech that will be more stable across changes to prod model and avoid wasting time waiting for test results every time something has to be changed there.

Guida contributor