Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / NVIDIA/radtts issues and pull requests

#32 - Straight through on unsupervised aligner

Issue - State: open - Opened by njellinas 8 months ago

#31 - Train custom voice instead of the default ljs speaker.

Issue - State: open - Opened by rajdeep1337 almost 1 year ago

#30 - recommend the steps of 1st-stage training.

Issue - State: closed - Opened by duj12 about 1 year ago

#29 - Training for singing models

Issue - State: open - Opened by sjkoelle about 1 year ago

#28 - Question about spectrogram normalization

Issue - State: closed - Opened by sjkoelle over 1 year ago - 1 comment

#27 - Inference with bgap models

Issue - State: closed - Opened by egorsmkv over 1 year ago

#26 - Compare with anyscale

Pull Request - State: closed - Opened by sjkoelle over 1 year ago

#25 - train decatndur

Issue - State: open - Opened by 11721206 over 1 year ago - 2 comments

#24 - why mix phone and word embedding

Issue - State: open - Opened by 11721206 over 1 year ago - 1 comment

#22 - More training configs

Pull Request - State: closed - Opened by sjkoelle almost 2 years ago

#20 - Certain texts in LJ speech unloadable

Issue - State: closed - Opened by sjkoelle almost 2 years ago - 1 comment

#19 - Output of voice conversion has source model's timbre, not destination models timbre

Issue - State: closed - Opened by mepc36 almost 2 years ago - 2 comments

#17 - Is it a mistake in README?

Issue - State: closed - Opened by egorsmkv almost 2 years ago - 1 comment

#16 - Here's a Colab notebook for using RADTTS [Documentation]

Issue - State: open - Opened by mepc36 almost 2 years ago

#15 - How to slow down the speed of the response?

Issue - State: closed - Opened by mepc36 almost 2 years ago - 3 comments

#14 - Trouble with inferencing without pitch and energy condition

Issue - State: open - Opened by tenebo about 2 years ago - 2 comments

#13 - Is it possible to do inference in real time?

Issue - State: closed - Opened by MJ54pwnz about 2 years ago

#12 - Required amount of data and iterations to train the model

Issue - State: open - Opened by Alexey322 about 2 years ago - 5 comments

#11 - Cannot train starting from pre-trained model b/c audio files not found

Issue - State: closed - Opened by mepc36 about 2 years ago - 1 comment

#10 - waveglow

Issue - State: open - Opened by HobisPL about 2 years ago - 1 comment

#9 - emotion = 'other' if len(d) == 3 else d[3] IndexError: list index out of range

Issue - State: open - Opened by Syed044 about 2 years ago - 6 comments

#8 - AttributeError: 'RADTTS' object has no attribute 'dur_pred_layer'

Issue - State: open - Opened by windowzzhhuu over 2 years ago - 11 comments

#7 - muffled audio output for custom dataset

Issue - State: closed - Opened by reubzdubz over 2 years ago - 7 comments

#6 - size mismatch for context_lstm.weight_ih_l0 and context_lstm.weight_ih_l0_reverse

Issue - State: open - Opened by skyler14 over 2 years ago - 13 comments

#5 - How to transfer speech style from another reference audio?

Issue - State: open - Opened by jiamingkong over 2 years ago - 3 comments

#4 - Dependencies are broken/incomplete, project deployment is hard to follow

Issue - State: open - Opened by skyler14 over 2 years ago - 1 comment

#3 - cannot start training from a pre-trained model

Issue - State: open - Opened by eschmidbauer over 2 years ago - 5 comments

#2 - Setting model paths in Voice conversion demo

Issue - State: closed - Opened by keeganstoner over 2 years ago - 1 comment