bshall/UniversalVocoding issues and pull requests

#24 - Help needed. Trying to get vocoder working with output from a ML Tracotron

Issue - State: open - Opened by michael-conrad almost 3 years ago - 5 comments

#23 - audio_slice_frames deprecation in v0.2

Issue - State: open - Opened by tarepan over 3 years ago - 1 comment

#22 - audio_slice_frames in v0.2

Issue - State: closed - Opened by tarepan over 3 years ago

#21 - How to improve performance

Issue - State: open - Opened by Kerry0123 almost 4 years ago - 2 comments

#20 - Why the embedding layer instead of the one-hot audio vector?

Issue - State: open - Opened by ivancarapinha almost 4 years ago - 1 comment

#19 - generate_audio questions

Issue - State: open - Opened by Kerry0123 almost 4 years ago

#18 - preprocessing_mel question

Issue - State: closed - Opened by Kerry0123 about 4 years ago - 6 comments

#17 - About Speaker Voice

Issue - State: closed - Opened by shoegazerstella about 4 years ago - 4 comments

#16 - How long does it takes to train from the scratch?

Issue - State: closed - Opened by sbkim052 about 4 years ago - 4 comments

#15 - Changing parameters

Issue - State: closed - Opened by sbkim052 about 4 years ago - 2 comments

#14 - Result remains little noise, but loss does not decrease

Issue - State: open - Opened by Approximetal over 4 years ago - 9 comments

#13 - Generating samples from generated Mel-spectrograms

Issue - State: closed - Opened by francislata almost 5 years ago - 3 comments

#12 - Usage of audio_slice_frames, sample_frames, pad

Issue - State: open - Opened by wade3han almost 5 years ago - 8 comments

#11 - Question about preprocess.py

Issue - State: closed - Opened by wade3han almost 5 years ago - 1 comment

#10 - 24kHz and 10 bit mu-law model

Issue - State: open - Opened by bshall about 5 years ago - 2 comments
Labels: enhancement, help wanted

#9 - What's the capacity of this network?

Issue - State: open - Opened by nkcdy about 5 years ago - 14 comments

#8 - mulaw encdoing

Issue - State: open - Opened by maximilianchen about 5 years ago - 1 comment

#7 - Inference speed comparison

Issue - State: open - Opened by sujeendran about 5 years ago - 1 comment
Labels: question

#6 - Result with other datasets

Issue - State: open - Opened by tarepan about 5 years ago - 1 comment

#5 - num_steps of training for those demo sample?

Issue - State: open - Opened by bayesrule about 5 years ago - 5 comments
Labels: question

#4 - About generated samples

Issue - State: open - Opened by sunnnnnnnny about 5 years ago - 1 comment
Labels: question

#3 - Generate audio from mag spectrogram

Issue - State: open - Opened by tunnermann about 5 years ago - 5 comments

#2 - path to waveform directory

Issue - State: closed - Opened by maximilianchen over 5 years ago - 3 comments

#1 - Simplified

Pull Request - State: closed - Opened by bshall over 5 years ago

Ecosyste.ms: Issues

GitHub / bshall/UniversalVocoding issues and pull requests