silero-models icon indicating copy to clipboard operation
silero-models copied to clipboard

Published 20 hours ago • verified publisher icon snakers4

Feature request - [slovenian language]

Open ppisljar opened this issue 1 year ago • 1 comments

🚀 Feature

Please add support for slovenian language, here you can find a quality dataset:

  • audio: https://www.clarin.si/repository/xmlui/handle/11356/1776
  • transcriptions: https://www.clarin.si/repository/xmlui/handle/11356/1772

Artur_B_Studio (inside the dataset) contains 50 hours of a single speaker recorded in a studio (high quality). In total there are 800 transcribed hours (multiple speakers, varying quality)

for phonemizer you can use espeak-ng with "sl" language ("slovenian" voice)

ppisljar avatar Jun 02 '23 05:06 ppisljar