mozilla / DeepSpeech

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Wrong pronunciation of short forms words like 'USA', 'UN' , 'MSN'.

Nimesh1993 opened this issue · comments

I tried to test with ljspeech tacotron2-DDC English model for below text:
"Short form of country names, USA stands for united states of america, UN stands for united nations , UK stands for united kingdom, ANN stands for artificial neural networks, MSN stands for microsoft networks."

It is pronouncing all short forms like 'USA', 'UN' , 'MSN', 'ANN', 'UK' in wrong way. Check the attached output.zip file.
output.zip

Is there any way to resolve this type of issue?

This is a TTS issue while this project is about STT.