Ecosyste.ms: Issues

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

GitHub / jaywalnut310/glow-tts issues and pull requests

#76 - [CONTRIBUTION] Speech Dataset Generator

Issue - State: open - Opened by davidmartinrius 9 months ago

#75 - [Question] about `intersperse` function.

Issue - State: open - Opened by chep0k about 1 year ago - 2 comments

#73 - DDI training compared to not DDI training

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

#72 - An explanation for the source code of finding the alignment path in GlowTTS?

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

#71 - With out Training DDI

Issue - State: open - Opened by johnny9696 over 2 years ago

#70 - Johnny

Pull Request - State: closed - Opened by johnny9696 over 2 years ago

#69 - Multi speaker training error

Issue - State: open - Opened by kumdori88 over 2 years ago - 11 comments

#67 - Can I apply MAS method to other model ?

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

#66 - Error using mel generated from glow-tts for hifi-gan training

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

#64 - RuntimeError: CUDA error: invalid device function

Issue - State: closed - Opened by tenebo almost 3 years ago

#63 - Glowtts melspectrogram to fine tune hifigan

Issue - State: open - Opened by michaellin99999 almost 3 years ago - 2 comments

#62 - Could not create monotonic_align

Issue - State: open - Opened by ankurdhuriya almost 3 years ago - 3 comments

#61 - Models for finetuning

Issue - State: open - Opened by sygi about 3 years ago

#60 - Output compared to Fastspeech2

Issue - State: open - Opened by debasish-mihup over 3 years ago

#59 - multi speaker

Issue - State: open - Opened by luantunez over 3 years ago

#58 - Different Languages us different amount of GPU memory

Issue - State: open - Opened by ohanoch over 3 years ago

#57 - GPU required or CPU-compatible?

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

#56 - Runtime Error: Multi speaker

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

#55 - Question about duration loss

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

#54 - Question regarding fine tunning

Issue - State: closed - Opened by debasish-mihup over 3 years ago - 15 comments

#52 - Getting assertion error for while training

Issue - State: closed - Opened by debasish-mihup over 3 years ago - 1 comment

#51 - Parallelization and GPU requirements

Issue - State: closed - Opened by patdflynn over 3 years ago - 2 comments

#50 - Problem with running on cuda 11.2

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

#50 - Problem with running on cuda 11.2

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

#48 - Regarding adding a Colab Notebook

Issue - State: open - Opened by sayakpaul almost 4 years ago - 3 comments

#48 - Regarding adding a Colab Notebook

Issue - State: open - Opened by sayakpaul almost 4 years ago - 3 comments

#47 - Create a demo file that allows users to easily run inference through browser

Pull Request - State: closed - Opened by abidlabs almost 4 years ago - 1 comment

#46 - A reshape problem in InvConvNear

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

#45 - any shared win prebuilt monotonic_align?

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

#44 - 已放弃 (吐核)python train.py -c $config -m $modeldir

Issue - State: closed - Opened by TaoTaoFu almost 4 years ago

#43 - Why putting a blank token between any two input tokens can improve pronunciation?

Issue - State: closed - Opened by shahuzi about 4 years ago - 7 comments

#42 - One question about the decoder compared with FastSpeech and Tacotron.

Issue - State: open - Opened by LeoniusChen about 4 years ago - 2 comments

#41 - Size of glowtts models

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

#39 - Transfer to tensorRT and using triton inference

Issue - State: open - Opened by andrey999333 about 4 years ago - 7 comments

#38 - GlowTTS with MultiBand Melgan

Issue - State: closed - Opened by Zarbuvit about 4 years ago - 7 comments

#37 - GPU not being utilized?

Issue - State: open - Opened by ohanoch about 4 years ago - 5 comments

#36 - ZeroDivisionError: float division by zero when training the model

Issue - State: open - Opened by mataym about 4 years ago - 3 comments

#35 - Working 'version' of WaveGlow

Issue - State: closed - Opened by dechubby about 4 years ago - 1 comment

#34 - There's no requirements file

Issue - State: open - Opened by 41WhiteElephants over 4 years ago - 1 comment

#33 - How to train a new model with dataset of diffirent language?

Issue - State: open - Opened by 41WhiteElephants over 4 years ago - 5 comments

#32 - Would you be willing to integrate this to Mozilla TTS?

Issue - State: closed - Opened by erogol over 4 years ago

#31 - Sharing the results of the Korean model learned in my voice

Issue - State: open - Opened by rishubil over 4 years ago - 1 comment

#30 - Idea on modeling different features of speech

Issue - State: open - Opened by RKorzeniowski over 4 years ago

#29 - griffin-lim gives strange output

Issue - State: closed - Opened by OnceJune over 4 years ago - 1 comment

#28 - Sharing my results. Glow-tts is incredibly impressive!

Issue - State: open - Opened by echelon over 4 years ago - 5 comments

#27 - Sharing Korean Glow-TTS Samples

Issue - State: open - Opened by Joovvhan over 4 years ago - 5 comments

#25 - Load checkpoints that are missing 'iteration', 'learning_rate' or 'optimizer' keys.

Pull Request - State: closed - Opened by CookiePPP over 4 years ago - 1 comment

#24 - trained with russian dataset, results do not sounds as good as demo samples

Issue - State: open - Opened by hadaev8 over 4 years ago - 2 comments

#23 - text embedding dimension

Issue - State: closed - Opened by Charlottecuc over 4 years ago - 6 comments

#22 - Any method could make the result more nature?

Issue - State: open - Opened by wotulong over 4 years ago - 3 comments

#21 - inference with pretrained model

Issue - State: closed - Opened by marshonhuckleberry over 4 years ago - 1 comment

#20 - inference

Issue - State: closed - Opened by marshonhuckleberry over 4 years ago - 1 comment

#19 - [ERROR] monotonic_align.core

Issue - State: open - Opened by pier314 over 4 years ago - 3 comments

#18 - Whats values of final losses?

Issue - State: closed - Opened by hadaev8 over 4 years ago - 2 comments

#17 - Log det Jacobian is wrong in Inv1x1Conv

Issue - State: closed - Opened by MokkeMeguru over 4 years ago - 5 comments

#16 - Number of training steps

Issue - State: open - Opened by sam1373 over 4 years ago - 1 comment

#15 - Gradient overflow and negative loss

Issue - State: closed - Opened by Charlottecuc over 4 years ago - 5 comments

#14 - Ideal size of gin_channels for multiple speaker embeddings?

Issue - State: open - Opened by echelon over 4 years ago - 3 comments

#13 - Add new speaker voice

Issue - State: open - Opened by marlon-br over 4 years ago - 5 comments

#12 - Why you do not use pytorch native layer norm?

Issue - State: closed - Opened by hadaev8 over 4 years ago - 7 comments

#11 - 멀티-스피커 버전 버그?

Issue - State: open - Opened by Ondal90 over 4 years ago - 1 comment

#10 - About speaker embedding

Issue - State: closed - Opened by Charlottecuc over 4 years ago - 3 comments

#9 - Compare with other parallel TTS

Issue - State: closed - Opened by chazo1994 over 4 years ago - 4 comments

#8 - How about the intelligibility and stability

Issue - State: closed - Opened by chazo1994 over 4 years ago - 1 comment

#7 - CUDA error. What version of CUDA are you running?

Issue - State: closed - Opened by echelon over 4 years ago - 2 comments

#6 - Loss value

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

#5 - Autoregressive flow instead of WaveGlow?

Issue - State: closed - Opened by janvainer over 4 years ago - 5 comments

#4 - [train.py] epoch당 진행률 계산

Issue - State: open - Opened by Sejik over 4 years ago - 2 comments

#3 - License?

Issue - State: closed - Opened by slckl over 4 years ago - 1 comment

#2 - run issue

Issue - State: closed - Opened by xinqipony over 4 years ago

#1 - q

Issue - State: closed - Opened by unwritten over 4 years ago