openvpi/DiffSinger

Issues

• Vocoder training code location

  #207 opened 14 days ago by SmoothKen
  1

• Inference DiffSinger

  #204 opened a month ago by Arseny5
  6

• Custom Trained DiffSinger Render Failed

  #186 opened 5 months ago by Alistair-zhong
  4

• In automatic optimization, `training_step` must return a Tensor, a dict, or None (where the step will be skipped).

  #197 opened 3 months ago by c7e715d1b04b17683718fb1e8944cc28
  7

• DiffSinger 制作合唱

  #201 opened 2 months ago by Alistair-zhong
  2

• ONNX Inference Scripts Documentation

  #198 opened 3 months ago by PeterFavero
  5

• Error training variance model

  #199 opened 3 months ago by Surya-29
  3

• Effects of transitioning mel_base from '10' to 'e'

  #195 opened 3 months ago by geckl
  2

• 关于唱法模型数据集

  #194 opened 4 months ago by lhc991025
  1

• Question regarding pitch models (Reflow vs DDPM)

  #193 opened 4 months ago by ariikamusic
  3

• Is removing background noise from audio beneficial to the quality of DiffSinger?

  #190 opened 4 months ago by Alistair-zhong
  2

• Batch evaluation inference scripts

  #155 opened 10 months ago by yqzhishen
  1

• 是否可以更改模型架构或者其他方式提升合成音质？

  #189 opened 5 months ago by ILG2021
  6

• Export Acoustic Model Error:"size mismatch for fs2.txt_embed.weight"

  #185 opened 5 months ago by Alistair-zhong
  1

• Tracking: development around Rectified Flow

  #182 opened 5 months ago by yqzhishen
  3

• Strange humming sound during `SP` & `AP`

  #179 opened 5 months ago by loct824
  3

• AttributeError on ReFlow

  #181 opened 6 months ago by colstone
  1

• run inference on my own checkpoint

  #130 opened a year ago by nestyme
  4

• onnx exports to incorrect folder

  #178 opened 6 months ago by agentasteriski
  1

• Inference from Raw Input

  #165 opened 6 months ago by Tox1cPhantom
  5

• Inference from OpenUTAU USTx -> DiffSinger DS not Carrying Over Parameters

  #180 opened 6 months ago by sillybillylili
  1

• ONNX inference 'depth' parameter

  #176 opened 7 months ago by loct824
  6

• TypeError running variance inference (previously working)

  #173 opened 7 months ago by blueyred
  1

• Torch2.2 Error Variance

  #168 opened 7 months ago by usasho
  5

• Support tension and voicing

  #171 opened 7 months ago by yqzhishen
  0

• 关于breathiness的控制问题

  #161 opened 8 months ago by mindrover
  0

• Error preventing preprocessing

  #160 opened 8 months ago by agentasteriski
  2

• Different timbres from the same singer. seperated into unique speakers, all sound identical in a multi-speaker model

  #158 opened 10 months ago by spicytigermeat
  8

• A Tensorboard update issue in the case of multiple graphics cards.

  #157 opened 10 months ago by KakaruHayate
  2

• Does ds_variance.py align phoneme durations to notes like how it is done in OpenUTAU?

  #147 opened 10 months ago by JieLuChen
  1

• Add gradient scale factor for duration predictor

  #151 opened 10 months ago by yqzhishen
  1

• Better normalization of variance parameters

  #152 opened a year ago by yqzhishen
  0

• Error exporting to ONNX

  #150 opened a year ago by github-axel-boidin
  3

• Melody encoder and ornaments modeling

  #142 opened a year ago by yqzhishen
  4

• Re-implement shallow diffusion

  #129 opened a year ago by yqzhishen
  0

• Apply for dataset

  #145 opened a year ago by li-henan
  0

• compatible with master version acoustic pre-train

  #141 opened a year ago by nestyme
  2

• Error failed to render

  #140 opened a year ago by gnloop
  8

• [MFA] Transform matrix for utterance 1-1 has bad dimension 40x112 versus feat dim 105

  #139 opened a year ago by idootop
  0

• running inference with acoustic model [question]

  #137 opened a year ago by nestyme
  4

• Training variance models from DS files

  #131 opened a year ago by yqzhishen
  0

• On the problem of phoneme loss when using Opencpop data set to train automatic pitch model

  #134 opened a year ago by Wangs-official
  2

• On the problem of missing three phonemes "ir", "E" and "En"

  #133 opened a year ago by Wangs-official
  1

• variance model onnx exporter

  #117 opened a year ago by blueyred
  10

• Make pauses / silence inside singing

  #126 opened a year ago by MrDiplodocus
  2

• Feature proposal: freeze specific parameters when finetuning

  #116 opened a year ago by yqzhishen
  0

• Conda install Diffsinger Error Data

  #124 opened a year ago by usasho
  2

• Can not export ONNX model

  #121 opened a year ago by Katistic
  2

• Phoneme duration predictions / note slur issue

  #112 opened a year ago by blueyred
  3

• How to use pretrained models?

  #109 opened a year ago by med1844
  8