NVIDIA/mellotron issues and pull requests

#42 - Pitch contour not being applied

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

#41 - Unable to reproduce decent quality generated audio with training data samples

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

#40 - Installation issues on Ubuntu 18.04

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

#39 - Adaptation

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

#39 - Adaptation

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

#38 - Singing voice from audio signal

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

#38 - Singing voice from audio signal

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

#37 - Training DB for Waveglow pretrained model in this repo

Issue - State: closed - Opened by hash2430 over 4 years ago - 3 comments

#37 - Training DB for Waveglow pretrained model in this repo

Issue - State: closed - Opened by hash2430 over 4 years ago - 3 comments

#36 - No of training iterations of pretrained model

Issue - State: open - Opened by alexvioni almost 5 years ago - 1 comment

#36 - No of training iterations of pretrained model

Issue - State: open - Opened by alexvioni almost 5 years ago - 1 comment

#35 - build(deps): bump tensorflow from 1.15 to 1.15.2

Pull Request - State: closed - Opened by dependabot[bot] almost 5 years ago
Labels: dependencies

#35 - build(deps): bump tensorflow from 1.15 to 1.15.2

Pull Request - State: closed - Opened by dependabot[bot] almost 5 years ago
Labels: dependencies

#34 - inference_noattention for new sequences

Issue - State: open - Opened by texpomru13 almost 5 years ago - 3 comments

#33 - Correction for text with punctuation and dash

Pull Request - State: open - Opened by hyunjoolee almost 5 years ago

#33 - Correction for text with punctuation and dash

Pull Request - State: open - Opened by hyunjoolee almost 5 years ago

#32 - LJS trained model?

Issue - State: closed - Opened by scottbouma almost 5 years ago - 2 comments

#32 - LJS trained model?

Issue - State: closed - Opened by scottbouma almost 5 years ago - 2 comments

#31 - The distinction between different speaker with mandarin dataset is not obvious.

Issue - State: open - Opened by chynphh almost 5 years ago - 2 comments

#31 - The distinction between different speaker with mandarin dataset is not obvious.

Issue - State: open - Opened by chynphh almost 5 years ago - 2 comments

#30 - Cannot resume training without quality loss

Issue - State: closed - Opened by AndroYD84 almost 5 years ago - 5 comments

#29 - how many epochs to get good results for libritts clean 100?

Issue - State: open - Opened by xilaili almost 5 years ago

#29 - how many epochs to get good results for libritts clean 100?

Issue - State: open - Opened by xilaili almost 5 years ago

#28 - How to fix problematic words with MusicXML parser?

Issue - State: open - Opened by AndroYD84 almost 5 years ago - 7 comments

#28 - How to fix problematic words with MusicXML parser?

Issue - State: open - Opened by AndroYD84 almost 5 years ago - 7 comments

#27 - Fixed CMUDict and ARPAbet conversion (p_arpabet is currently not used)

Pull Request - State: closed - Opened by xDuck almost 5 years ago - 1 comment

#27 - Fixed CMUDict and ARPAbet conversion (p_arpabet is currently not used)

Pull Request - State: closed - Opened by xDuck almost 5 years ago - 1 comment

#26 - hparams trainings settings

Issue - State: closed - Opened by peter1000 almost 5 years ago - 2 comments

#25 - correction of typos link (ignored) in README

Pull Request - State: closed - Opened by texpomru13 almost 5 years ago

#25 - correction of typos link (ignored) in README

Pull Request - State: closed - Opened by texpomru13 almost 5 years ago

#24 - RuntimeError: CUDA out of memory

Issue - State: closed - Opened by texpomru13 almost 5 years ago - 5 comments

#24 - RuntimeError: CUDA out of memory

Issue - State: closed - Opened by texpomru13 almost 5 years ago - 5 comments

#23 - correct f0 frame_length error

Pull Request - State: open - Opened by JeffpanUK almost 5 years ago - 1 comment

#23 - correct f0 frame_length error

Pull Request - State: open - Opened by JeffpanUK almost 5 years ago - 1 comment

#22 - try other language？

Issue - State: open - Opened by daxiangpanda almost 5 years ago - 31 comments

#22 - try other language？

Issue - State: open - Opened by daxiangpanda almost 5 years ago - 31 comments

#21 - long dataset need more video memory？

Issue - State: closed - Opened by daxiangpanda almost 5 years ago - 4 comments

#21 - long dataset need more video memory？

Issue - State: closed - Opened by daxiangpanda almost 5 years ago - 4 comments

#20 - Style tokens as guide rather than 1:1 transfer

Issue - State: closed - Opened by richardburleigh almost 5 years ago - 4 comments

#20 - Style tokens as guide rather than 1:1 transfer

Issue - State: closed - Opened by richardburleigh almost 5 years ago - 4 comments

#19 - Yin pitch set to minimum 100 Hz

Issue - State: closed - Opened by drfeinberg almost 5 years ago - 2 comments

#19 - Yin pitch set to minimum 100 Hz

Issue - State: closed - Opened by drfeinberg almost 5 years ago - 2 comments

#18 - confused about source speaker id in style and rhythm transfer

Issue - State: open - Opened by JeffpanUK almost 5 years ago - 4 comments

#18 - confused about source speaker id in style and rhythm transfer

Issue - State: open - Opened by JeffpanUK almost 5 years ago - 4 comments

#17 - Sampling rate used for pretrained model of LibriTTS

Issue - State: closed - Opened by hash2430 almost 5 years ago - 1 comment

#16 - cpu inference?

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

#16 - cpu inference?

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

#15 - Remove dropout from decoder cell state

Pull Request - State: open - Opened by richardburleigh almost 5 years ago - 5 comments

#15 - Remove dropout from decoder cell state

Pull Request - State: open - Opened by richardburleigh almost 5 years ago - 5 comments

#14 - The most optimal audio settings for training dataset preparation?

Issue - State: open - Opened by AndroYD84 almost 5 years ago - 10 comments

#14 - The most optimal audio settings for training dataset preparation?

Issue - State: open - Opened by AndroYD84 almost 5 years ago - 10 comments

#13 - Cannot train with multi GPUs

Issue - State: closed - Opened by Yablon almost 5 years ago - 7 comments

#13 - Cannot train with multi GPUs

Issue - State: closed - Opened by Yablon almost 5 years ago - 7 comments

#12 - can you provide more musicxml file to test this model?

Issue - State: closed - Opened by daxiangpanda almost 5 years ago - 7 comments

#12 - can you provide more musicxml file to test this model?

Issue - State: closed - Opened by daxiangpanda almost 5 years ago - 7 comments

#11 - How to use the Yin algorithm compute GPE FFE

Issue - State: closed - Opened by xiaolkai almost 5 years ago - 2 comments

#11 - How to use the Yin algorithm compute GPE FFE

Issue - State: closed - Opened by xiaolkai almost 5 years ago - 2 comments

#10 - regarding text cleaner

Issue - State: closed - Opened by yxt132 almost 5 years ago - 1 comment

#10 - regarding text cleaner

Issue - State: closed - Opened by yxt132 almost 5 years ago - 1 comment

#9 - error during inference

Issue - State: closed - Opened by yxt132 almost 5 years ago - 2 comments

#9 - error during inference

Issue - State: closed - Opened by yxt132 almost 5 years ago - 2 comments

#8 - inference on COLAB

Issue - State: open - Opened by yhgon almost 5 years ago

#7 - Need more info for training and inference

Issue - State: closed - Opened by AndroYD84 almost 5 years ago - 6 comments

#7 - Need more info for training and inference

Issue - State: closed - Opened by AndroYD84 almost 5 years ago - 6 comments

#6 - Update requirements.txt

Pull Request - State: closed - Opened by yhgon almost 5 years ago - 1 comment

#5 - Update README.md

Pull Request - State: closed - Opened by yhgon almost 5 years ago - 1 comment

#5 - Update README.md

Pull Request - State: closed - Opened by yhgon almost 5 years ago - 1 comment

#4 - Generic Inference

Issue - State: closed - Opened by CookiePPP almost 5 years ago - 4 comments

#4 - Generic Inference

Issue - State: closed - Opened by CookiePPP almost 5 years ago - 4 comments

#3 - Specify Tensorflow version

Pull Request - State: closed - Opened by robinsloan almost 5 years ago - 1 comment

#2 - Bump nltk from 3.3 to 3.4.5

Pull Request - State: closed - Opened by dependabot[bot] almost 5 years ago
Labels: dependencies

#1 - Update README.md

Pull Request - State: closed - Opened by KinglittleQ almost 5 years ago

#1 - Update README.md

Pull Request - State: closed - Opened by KinglittleQ almost 5 years ago

GitHub / NVIDIA/mellotron issues and pull requests