NVIDIA mellotron issues

NVIDIA / mellotron

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

BSD 3-Clause "New" or "Revised" License

855 stars 183 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Replace split word_tokenize to deal with punctuations.

#75 sungjae-cho closed 4 years ago
14
How to choose a target speaker for generating voice

#74 deepuvikraman closed 4 years ago
5
modules.py: add input lengths processing to ReferenceEncoder

#73 hubeibei007 closed 4 years ago
1
why ignore speaker embedding?

#72 zzw922cn opened 4 years ago
2
ReferenceEncoder did not use the actual mel lengths

#71 hubeibei007 closed 4 years ago
2
Question about the gender of the Libri dataset used by Mellotron mention in the published article

#70 TitiAffandi opened 4 years ago
1
require large memory

#69 aijianiula0601 opened 4 years ago
3
Speaker order is randomised while loading - why?

#68 karkirowle closed 4 years ago
1
Difference between CMUDict of None?

#67 lqniunjunlper opened 4 years ago
1
Inference failed

#66 lqniunjunlper opened 4 years ago
1
Inference bug?

#65 lqniunjunlper closed 4 years ago
1
Style not being applied

#64 kannadaraj opened 4 years ago
4
Gradient overflow with Mixed Precision Training

#63 MinHyung-Kang opened 4 years ago
1
Using own text to generate speech using Mellotron

#62 astricks closed 4 years ago
8
Adding another speaker

#61 JakubReha closed 4 years ago
5
Question about custom dataset

#60 LucasRotsen closed 4 years ago
2
The speaker ids are misaligned in inference.ipynb

#59 pneumoman closed 4 years ago
7
[QUESTION] About lyrics hyphenation

#58 loretoparisi closed 4 years ago
5
Generic Text-to-Speech Inference

#57 GreenGarnets opened 4 years ago
1
Funky warble on sustained sung notes from a MUSICXML file

#56 josharmenta opened 4 years ago
2
Information about p_teacher_forcing hyperparameter

#55 paarthneekhara closed 4 years ago
3
Synthesized voice does not correspond to the speaker id

#54 paarthneekhara closed 4 years ago
4
Singing Voice from Music Score

#53 Sangkikim-77 closed 4 years ago
4
Inference troubles on Windows

#52 camjac251 opened 4 years ago
21
Docker

#51 pneumoman opened 4 years ago
0
CUDA out of memory while running inference file

#50 pathakmukul closed 4 years ago
7
Windows Anaconda

#49 camjac251 opened 4 years ago
5
How to fine tune a new voice using pretrained model

#48 mathigatti opened 4 years ago
3
Warning Message in yin

#47 pneumoman closed 3 years ago
5
synthesized speaker quality changed

#46 kannadaraj opened 4 years ago
5
The effect of passing in the original MEL seems minimal

#45 pneumoman closed 4 years ago
3
Dimensions mismatch when using pretrained model

#44 mathigatti closed 4 years ago
1
Question regarding paper

#43 hash2430 opened 4 years ago
4
Pitch contour not being applied

#42 tebin closed 4 years ago
2
Unable to reproduce decent quality generated audio with training data samples

#41 rohanbadlani closed 4 years ago
1
Installation issues on Ubuntu 18.04

#40 loretoparisi opened 4 years ago
1
Adaptation

#39 karkirowle opened 4 years ago
5
Singing voice from audio signal

#38 tebin closed 4 years ago
3
Training DB for Waveglow pretrained model in this repo

#37 hash2430 closed 4 years ago
3
No of training iterations of pretrained model

#36 alexvioni opened 4 years ago
1
build(deps): bump tensorflow from 1.15 to 1.15.2

#35 dependabot[bot] closed 4 years ago
0
inference_noattention for new sequences

#34 texpomru13 opened 4 years ago
3
Correction for text with punctuation and dash

#33 hyunjoolee opened 4 years ago
0
LJS trained model?

#32 scottbouma closed 4 years ago
2
The distinction between different speaker with mandarin dataset is not obvious.

#31 chynphh opened 4 years ago
2
Cannot resume training without quality loss

#30 AndroYD84 closed 4 years ago
5
how many epochs to get good results for libritts clean 100?

#29 xilaili opened 4 years ago
0
How to fix problematic words with MusicXML parser?

#28 AndroYD84 opened 4 years ago
7
Fixed CMUDict and ARPAbet conversion (p_arpabet is currently not used)

#27 xDuck closed 4 years ago
1
hparams trainings settings

#26 peter1000 closed 4 years ago
2

Previous Next