maum-ai/assem-vc issues and pull requests

#41 - Where can I get audio samples? The link in the README is broken.

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

#40 - Training Cotatron has a problem

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

#39 - Cross-lingual supported?

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

#38 - teacher-forcing

Issue - State: open - Opened by joan126 over 2 years ago - 1 comment

#37 - bibtex update ICASSP2022

Pull Request - State: closed - Opened by junjun3518 almost 3 years ago
Labels: documentation

#36 - How to split singing voices

Issue - State: open - Opened by betty97 almost 3 years ago

#35 - other models

Issue - State: open - Opened by Ruinmou almost 3 years ago

#34 - Build custom non-English dataset with ARPABET

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

#33 - Extending to n+1 target speakers using pretrained Cotatron

Issue - State: open - Opened by shaun-mathew almost 3 years ago

#32 - 어떻게해야 모델을 한글 음소로 학습시킬 수 있나요?

Issue - State: closed - Opened by Cardroid about 3 years ago - 2 comments

#31 - Changin the sampling rate

Issue - State: closed - Opened by cnamuangtoun about 3 years ago - 3 comments

#30 - Trouble importing AttrDict

Issue - State: open - Opened by imminentarchon about 3 years ago - 1 comment

#29 - Speech+Transcript conditioned phoneme recognition as an alternative to G2P

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

#28 - singer update

Pull Request - State: closed - Opened by junjun3518 over 3 years ago

#27 - Controllable and Interpretable Singing Voice Decomposition via Assem-VC

Issue - State: open - Opened by AK391 over 3 years ago - 9 comments

#26 - Singer Page

Pull Request - State: closed - Opened by junjun3518 over 3 years ago

#25 - Training HIFI-GAN faster

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

#24 - Regarding teacher forcing to calculate alignment

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

#23 - Best way to extend the model to a new speaker

Issue - State: closed - Opened by vishalbhavani over 3 years ago - 6 comments

#22 - One-to-Many

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

#21 - NaN loss on cotatron_trainer

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

#20 - Reason to use speaker encoder over speaker embeddings?

Issue - State: closed - Opened by dunky11 over 3 years ago - 2 comments

#19 - Bump pyyaml from 5.3.1 to 5.4

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

#18 - Upload Pretrained Weight & Bugfix

Pull Request - State: closed - Opened by wookladin over 3 years ago

#17 - Pre-trained model

Issue - State: closed - Opened by jJohnny342 over 3 years ago - 1 comment

#16 - how many hours of speakers voice will it need, to finetune this model?

Issue - State: closed - Opened by amelieyu1989 over 3 years ago - 1 comment

#14 - 한글 데이터 학습시 혀짧은 소리

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

#14 - 한글 데이터 학습시 혀짧은 소리

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

#13 - Possible bottleneck?

Issue - State: open - Opened by Vadim2S over 3 years ago - 3 comments

#12 - Is chn.residual_out missing in config/global/default.yaml ?

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

#12 - Is chn.residual_out missing in config/global/default.yaml ?

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

#11 - Resolving metadata and preprocessing issues

Pull Request - State: closed - Opened by wookladin over 3 years ago

#10 - Question about GTA of mel-spectograms

Issue - State: closed - Opened by dunky11 over 3 years ago - 2 comments

#9 - bugfix: prenet dropout should be 0.5

Pull Request - State: closed - Opened by wookladin over 3 years ago

#8 - Enable GTA finetuning & Bugfix

Pull Request - State: closed - Opened by wookladin over 3 years ago

#7 - make cotatron's training setting stable

Pull Request - State: closed - Opened by wookladin over 3 years ago

#6 - Update README.md

Pull Request - State: closed - Opened by wookladin over 3 years ago

#5 - Audio samples sound great! I have a few questions.

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

#4 - Speaker encoder

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

#3 - Which Hi-Fi gan version did you use?

Issue - State: closed - Opened by faranaziz almost 4 years ago - 3 comments

#2 - many to many, any to any 질문

Issue - State: closed - Opened by Moon-sung-woo almost 4 years ago - 1 comment

#1 - Code release?

Issue - State: closed - Opened by Devetec almost 4 years ago - 11 comments

GitHub / maum-ai/assem-vc issues and pull requests