openvpi/DiffSinger
An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
PythonApache-2.0
Issues
- 1
Vocoder training code location
#207 opened by SmoothKen - 6
Inference DiffSinger
#204 opened by Arseny5 - 4
Custom Trained DiffSinger Render Failed
#186 opened by Alistair-zhong - 7
In automatic optimization, `training_step` must return a Tensor, a dict, or None (where the step will be skipped).
#197 opened by c7e715d1b04b17683718fb1e8944cc28 - 2
DiffSinger 制作合唱
#201 opened by Alistair-zhong - 5
ONNX Inference Scripts Documentation
#198 opened by PeterFavero - 3
Error training variance model
#199 opened by Surya-29 - 2
Effects of transitioning mel_base from '10' to 'e'
#195 opened by geckl - 1
- 3
Question regarding pitch models (Reflow vs DDPM)
#193 opened by ariikamusic - 2
Is removing background noise from audio beneficial to the quality of DiffSinger?
#190 opened by Alistair-zhong - 1
Batch evaluation inference scripts
#155 opened by yqzhishen - 6
是否可以更改模型架构或者其他方式提升合成音质?
#189 opened by ILG2021 - 1
- 3
Tracking: development around Rectified Flow
#182 opened by yqzhishen - 3
Strange humming sound during `SP` & `AP`
#179 opened by loct824 - 1
AttributeError on ReFlow
#181 opened by colstone - 4
run inference on my own checkpoint
#130 opened by nestyme - 1
onnx exports to incorrect folder
#178 opened by agentasteriski - 5
Inference from Raw Input
#165 opened by Tox1cPhantom - 1
Inference from OpenUTAU USTx -> DiffSinger DS not Carrying Over Parameters
#180 opened by sillybillylili - 6
ONNX inference 'depth' parameter
#176 opened by loct824 - 1
- 5
Torch2.2 Error Variance
#168 opened by usasho - 0
Support tension and voicing
#171 opened by yqzhishen - 0
关于breathiness的控制问题
#161 opened by mindrover - 2
Error preventing preprocessing
#160 opened by agentasteriski - 8
Different timbres from the same singer. seperated into unique speakers, all sound identical in a multi-speaker model
#158 opened by spicytigermeat - 2
- 1
Does ds_variance.py align phoneme durations to notes like how it is done in OpenUTAU?
#147 opened by JieLuChen - 1
Add gradient scale factor for duration predictor
#151 opened by yqzhishen - 0
Better normalization of variance parameters
#152 opened by yqzhishen - 3
Error exporting to ONNX
#150 opened by github-axel-boidin - 4
Melody encoder and ornaments modeling
#142 opened by yqzhishen - 0
Re-implement shallow diffusion
#129 opened by yqzhishen - 0
Apply for dataset
#145 opened by li-henan - 2
compatible with master version acoustic pre-train
#141 opened by nestyme - 8
Error failed to render
#140 opened by gnloop - 0
[MFA] Transform matrix for utterance 1-1 has bad dimension 40x112 versus feat dim 105
#139 opened by idootop - 4
running inference with acoustic model [question]
#137 opened by nestyme - 0
Training variance models from DS files
#131 opened by yqzhishen - 2
On the problem of phoneme loss when using Opencpop data set to train automatic pitch model
#134 opened by Wangs-official - 1
- 10
variance model onnx exporter
#117 opened by blueyred - 2
Make pauses / silence inside singing
#126 opened by MrDiplodocus - 0
- 2
Conda install Diffsinger Error Data
#124 opened by usasho - 2
Can not export ONNX model
#121 opened by Katistic - 3
Phoneme duration predictions / note slur issue
#112 opened by blueyred - 8
How to use pretrained models?
#109 opened by med1844