SailorWEI comments

Results 19 comments of


                                            SailorWEI

How to view the result of the conversion？

"get_wav_batch" seems note in data_load.py, anyone run this successfully?

Any alternative for TIMIT dataset which is free .or else , where can i get free TIMIT dataset (630 speakers)?

http://search.language-archives.org/record.html?id=www_ldc_upenn_edu_LDC93S1W

Tips for generating good results.

Hi @carlfm01 , I just hear your spanish case. If it's trained with dataset which has a phoneme label?

Tips for generating good results.

Sounds interesting! @carlfm01 , I would like to learn and try your method, pls share with we. Email: [email protected]. Thanks a lot~

Tips for generating good results.

Thanks, I'll try. @carlfm01

Tips for generating good results.

I have a question about the generated data, @carlfm01 . For the Net1 training, TIMIT dataset used. TIMIT contains **630** speakers' utterances and corresponding phones that speaks similar sentences. The...

Tips for generating good results.

Sounds much better, great! @carlfm01

Tips for generating good results.

Hi @carlfm01 , python 2.7 and tf 1.8.0. The log file is as below. Thanks for your help of data. Maybe I can try to generate Chinese data for Net1...

Requirement for the data if we train model for a new person, or for a new language.

Maybe it's proper to move the discussions here. https://github.com/andabi/deep-voice-conversion/issues/59#issuecomment-422668930 https://github.com/andabi/deep-voice-conversion/issues/59#issuecomment-422680151 > Hi @sailor88128 , your audio sounds pretty good. I think you should train little more and then convert changing...