Giters

ming024 / FastSpeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

The numbers of the audio samples and speakers mismatch of LibriTTS dataset

shiyanpei0826 opened this issue · comments

commented

Hi

Your project and implementation is fantastic, I am learning our implementations

However, when I download your alignment Textgrids of Libritts, I found the numbers are much less than that of original Libritts dataset

Can you please share the details of alignments?

Thank you.