Ecosyste.ms: Issues

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

GitHub / NVIDIA/mellotron issues and pull requests

#100 - NoneType' object is not iterable

Issue - State: open - Opened by shaokun11 over 3 years ago

#100 - NoneType' object is not iterable

Issue - State: open - Opened by shaokun11 over 3 years ago

#99 - build(deps): bump tensorflow from 1.15.2 to 2.5.0

Pull Request - State: closed - Opened by dependabot[bot] over 3 years ago - 1 comment
Labels: dependencies

#99 - build(deps): bump tensorflow from 1.15.2 to 2.5.0

Pull Request - State: closed - Opened by dependabot[bot] over 3 years ago - 1 comment
Labels: dependencies

#98 - colab error

Issue - State: open - Opened by mochacat2001 over 3 years ago - 2 comments

#98 - colab error

Issue - State: open - Opened by mochacat2001 over 3 years ago - 2 comments

#97 - Can I use TensorRT to speed up model inference?

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

#97 - Can I use TensorRT to speed up model inference?

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

#96 - Something wrong with text padding

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

#96 - Something wrong with text padding

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

#95 - Is there a way to extract character durations?

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

#95 - Is there a way to extract character durations?

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

#94 - Fix mel inputs passed to GST Reference Encoder

Pull Request - State: open - Opened by ilya16 over 3 years ago

#93 - Could you tell me why use speaker id?

Issue - State: open - Opened by Moon-sung-woo almost 4 years ago

#93 - Could you tell me why use speaker id?

Issue - State: open - Opened by Moon-sung-woo almost 4 years ago

#92 - hparams for libritts training

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

#92 - hparams for libritts training

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

#91 - Where is the singer datdaset?

Issue - State: open - Opened by c1a1o1 almost 4 years ago - 1 comment

#91 - Where is the singer datdaset?

Issue - State: open - Opened by c1a1o1 almost 4 years ago - 1 comment

#90 - Help needed w.r.t. inference

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

#90 - Help needed w.r.t. inference

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

#89 - Can I transfer only rhythm or pitch between two audio ？

Issue - State: open - Opened by niu0717 almost 4 years ago

#89 - Can I transfer only rhythm or pitch between two audio ？

Issue - State: open - Opened by niu0717 almost 4 years ago

#88 - rhythm not good so the inference audio output is weird？

Issue - State: open - Opened by ryanjfdeng1 almost 4 years ago

#87 - build(deps): bump tensorflow from 1.15.2 to 2.3.1

Pull Request - State: closed - Opened by dependabot[bot] almost 4 years ago - 1 comment
Labels: dependencies

#87 - build(deps): bump tensorflow from 1.15.2 to 2.3.1

Pull Request - State: closed - Opened by dependabot[bot] almost 4 years ago - 1 comment
Labels: dependencies

#86 - How can I speed up or slow down the output audio?

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

#86 - How can I speed up or slow down the output audio?

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

#85 - Inference error

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

#85 - Inference error

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

#84 - build(deps): bump tensorflow from 1.15.2 to 1.15.4

Pull Request - State: closed - Opened by dependabot[bot] about 4 years ago - 1 comment
Labels: dependencies

#84 - build(deps): bump tensorflow from 1.15.2 to 1.15.4

Pull Request - State: closed - Opened by dependabot[bot] about 4 years ago - 1 comment
Labels: dependencies

#83 - Corrected 'cmudict' to 'dictionary' in __init__.py

Pull Request - State: closed - Opened by Jeevesh8 about 4 years ago

#82 - Small necessary corrections in text/__init__.py

Pull Request - State: closed - Opened by Jeevesh8 about 4 years ago - 3 comments

#82 - Small necessary corrections in text/__init__.py

Pull Request - State: closed - Opened by Jeevesh8 about 4 years ago - 3 comments

#81 - number of epoch issue

Issue - State: closed - Opened by yuzuda283 about 4 years ago - 1 comment

#81 - number of epoch issue

Issue - State: closed - Opened by yuzuda283 about 4 years ago - 1 comment

#79 - Update sequence_to_text (symbol_id.item())

Pull Request - State: open - Opened by Sejik about 4 years ago

#78 - Inference with our own text on pretrained model

Issue - State: open - Opened by xw1324832579 about 4 years ago

#77 - Strange query input shape of multihead attention in STL

Issue - State: closed - Opened by elch10 about 4 years ago - 1 comment

#77 - Strange query input shape of multihead attention in STL

Issue - State: closed - Opened by elch10 about 4 years ago - 1 comment

#76 - error in the model training on libritts data

Issue - State: closed - Opened by raymond00000 about 4 years ago - 9 comments

#75 - Replace split word_tokenize to deal with punctuations.

Pull Request - State: closed - Opened by sungjae-cho over 4 years ago - 14 comments

#74 - How to choose a target speaker for generating voice

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

#74 - How to choose a target speaker for generating voice

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

#73 - modules.py: add input lengths processing to ReferenceEncoder

Pull Request - State: closed - Opened by hubeibei007 over 4 years ago - 1 comment

#73 - modules.py: add input lengths processing to ReferenceEncoder

Pull Request - State: closed - Opened by hubeibei007 over 4 years ago - 1 comment

#72 - why ignore speaker embedding?

Issue - State: open - Opened by zzw922cn over 4 years ago - 2 comments

#72 - why ignore speaker embedding?

Issue - State: open - Opened by zzw922cn over 4 years ago - 2 comments

#71 - ReferenceEncoder did not use the actual mel lengths

Issue - State: closed - Opened by hubeibei007 over 4 years ago - 2 comments

#71 - ReferenceEncoder did not use the actual mel lengths

Issue - State: closed - Opened by hubeibei007 over 4 years ago - 2 comments

#69 - require large memory

Issue - State: open - Opened by aijianiula0601 over 4 years ago - 3 comments

#69 - require large memory

Issue - State: open - Opened by aijianiula0601 over 4 years ago - 3 comments

#68 - Speaker order is randomised while loading - why?

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

#68 - Speaker order is randomised while loading - why?

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

#67 - Difference between CMUDict of None?

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

#66 - Inference failed

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

#66 - Inference failed

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

#65 - Inference bug?

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

#65 - Inference bug?

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

#64 - Style not being applied

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

#63 - Gradient overflow with Mixed Precision Training

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

#62 - Using own text to generate speech using Mellotron

Issue - State: closed - Opened by astricks over 4 years ago - 8 comments

#62 - Using own text to generate speech using Mellotron

Issue - State: closed - Opened by astricks over 4 years ago - 8 comments

#61 - Adding another speaker

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

#61 - Adding another speaker

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

#60 - Question about custom dataset

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

#60 - Question about custom dataset

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

#59 - The speaker ids are misaligned in inference.ipynb

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

#59 - The speaker ids are misaligned in inference.ipynb

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

#58 - [QUESTION] About lyrics hyphenation

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

#58 - [QUESTION] About lyrics hyphenation

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

#57 - Generic Text-to-Speech Inference

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

#56 - Funky warble on sustained sung notes from a MUSICXML file

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

#55 - Information about p_teacher_forcing hyperparameter

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

#54 - Synthesized voice does not correspond to the speaker id

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

#54 - Synthesized voice does not correspond to the speaker id

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

#53 - Singing Voice from Music Score

Issue - State: closed - Opened by Sangkikim-77 over 4 years ago - 4 comments

#52 - Inference troubles on Windows

Issue - State: open - Opened by camjac251 over 4 years ago - 21 comments

#52 - Inference troubles on Windows

Issue - State: open - Opened by camjac251 over 4 years ago - 21 comments

#51 - Docker

Pull Request - State: open - Opened by pneumoman over 4 years ago

#51 - Docker

Pull Request - State: open - Opened by pneumoman over 4 years ago

#50 - CUDA out of memory while running inference file

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

#50 - CUDA out of memory while running inference file

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

#49 - Windows Anaconda

Issue - State: open - Opened by camjac251 over 4 years ago - 5 comments

#49 - Windows Anaconda

Issue - State: open - Opened by camjac251 over 4 years ago - 5 comments

#48 - How to fine tune a new voice using pretrained model

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

#48 - How to fine tune a new voice using pretrained model

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

#47 - Warning Message in yin

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

#47 - Warning Message in yin

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

#46 - synthesized speaker quality changed

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

#46 - synthesized speaker quality changed

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

#45 - The effect of passing in the original MEL seems minimal

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

#44 - Dimensions mismatch when using pretrained model

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

#43 - Question regarding paper

Issue - State: open - Opened by hash2430 over 4 years ago - 4 comments

#43 - Question regarding paper

Issue - State: open - Opened by hash2430 over 4 years ago - 4 comments