ROBERT MCDOWELL
ROBERT MCDOWELL
well, your pdf and epub contains only JPG images, no text at all. It would need an OCR to scan and convert it in text first..... we planned to develop...
could you tell me which sentences are missing?
about intonation, depends the model you are using, it's not our job to fix it. depend the language and TTS you are using too. it's up to you to train...
the missing sentences is probably due to the special chars like paragraph dots, parenethesis with non latin chars etc... for the pauses missing, it really depends from the source of...
OCR (image scan to text) has been added to the PDF files only in the next coming release.
correction: PDF, PNG, TIF, TIFF with multiple pages, BMP, JPG, JPEG are supported.
are you using our last git or v2.0.0 ? I see you are using your python system. are you running eb2ab with docker? try to uninstall num2words and downgrade with...
the right iso fo czech is "cs", "cse", "cze", so it's on coqui-tts to modify it to 'cs', we are working with an active fork and you can tell them...
meanwhile if you find another TTS engine with the same or better quality than coqui-TTS so we can implement it.
that's a good news, so we can include it as fairseq model even if it's not... most of these EU languages are not supported by mms fairseq so it's a...