mozilla/DeepSpeech
Voir sur GitHubReplace LDC93S1 sample in prod tests with something else
Open
#2 732 ouverte le 10 févr. 2020
good first bughelp wanted
Métriques du dépôt
- Stars
- (26 755 stars)
- Métriques de merge PR
- (Aucune PR mergée en 30 j)
Description
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.