Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / openvpi/DiffSinger issues and pull requests
#207 - Vocoder training code location
Issue -
State: closed - Opened by SmoothKen 12 days ago
- 1 comment
#206 - Lynxnet outnorm
Pull Request -
State: closed - Opened by KakaruHayate 15 days ago
#205 - Support exporting user-defined vocoder package names in dsconfig.yaml
Pull Request -
State: open - Opened by komisteng 16 days ago
#204 - Inference DiffSinger
Issue -
State: closed - Opened by Arseny5 about 1 month ago
- 6 comments
#202 - Faster NSF inference
Pull Request -
State: closed - Opened by yxlllc about 2 months ago
#201 - DiffSinger 制作合唱
Issue -
State: closed - Opened by Alistair-zhong 2 months ago
- 2 comments
#200 - [DONE]New AUX_Decoder/Backbone Network : LYNXNet
Pull Request -
State: closed - Opened by KakaruHayate 2 months ago
#199 - Error training variance model
Issue -
State: closed - Opened by Surya-29 3 months ago
- 3 comments
#198 - ONNX Inference Scripts Documentation
Issue -
State: open - Opened by PeterFavero 3 months ago
- 5 comments
#197 - In automatic optimization, `training_step` must return a Tensor, a dict, or None (where the step will be skipped).
Issue -
State: closed - Opened by c7e715d1b04b17683718fb1e8944cc28 3 months ago
- 7 comments
#196 - Using VR model to estimate variance parameters
Pull Request -
State: closed - Opened by yxlllc 3 months ago
#195 - Effects of transitioning mel_base from '10' to 'e'
Issue -
State: closed - Opened by geckl 3 months ago
- 2 comments
#194 - 关于唱法模型数据集
Issue -
State: open - Opened by lhc991025 4 months ago
- 1 comment
#193 - Question regarding pitch models (Reflow vs DDPM)
Issue -
State: open - Opened by ariikamusic 4 months ago
- 3 comments
#191 - Mode 'parallel' for EncSALayer to speed up infer on ONNX
Pull Request -
State: closed - Opened by KakaruHayate 4 months ago
#190 - Is removing background noise from audio beneficial to the quality of DiffSinger?
Issue -
State: closed - Opened by Alistair-zhong 4 months ago
- 2 comments
#189 - 是否可以更改模型架构或者其他方式提升合成音质?
Issue -
State: closed - Opened by ILG2021 5 months ago
- 6 comments
#188 - Add important notice on experimental branches
Pull Request -
State: open - Opened by RigoLigoRLC 5 months ago
- 2 comments
#187 - Fix D4C waveform decompositioning threshold (improves sound quality of variance models)
Pull Request -
State: closed - Opened by lottev1991 5 months ago
- 2 comments
#186 - Custom Trained DiffSinger Render Failed
Issue -
State: closed - Opened by Alistair-zhong 5 months ago
- 4 comments
#185 - Export Acoustic Model Error:"size mismatch for fs2.txt_embed.weight"
Issue -
State: closed - Opened by Alistair-zhong 5 months ago
- 1 comment
#184 - New generative model algorithm: Rectified Flow
Pull Request -
State: closed - Opened by autumn-2-net 5 months ago
#182 - Tracking: development around Rectified Flow
Issue -
State: closed - Opened by yqzhishen 6 months ago
- 3 comments
#181 - AttributeError on ReFlow
Issue -
State: closed - Opened by colstone 6 months ago
- 1 comment
#180 - Inference from OpenUTAU USTx -> DiffSinger DS not Carrying Over Parameters
Issue -
State: closed - Opened by sillybillylili 6 months ago
- 1 comment
#179 - Strange humming sound during `SP` & `AP`
Issue -
State: closed - Opened by loct824 6 months ago
- 3 comments
#178 - onnx exports to incorrect folder
Issue -
State: closed - Opened by agentasteriski 6 months ago
- 1 comment
#177 - Finish docs for v2.3.0 release
Pull Request -
State: closed - Opened by yqzhishen 6 months ago
#176 - ONNX inference 'depth' parameter
Issue -
State: closed - Opened by loct824 7 months ago
- 6 comments
#175 - Support using `e` as the base number of the log mel-spectrogram
Pull Request -
State: closed - Opened by yqzhishen 7 months ago
#173 - TypeError running variance inference (previously working)
Issue -
State: closed - Opened by blueyred 7 months ago
- 1 comment
#172 - Drop support for some old features and behaviors
Pull Request -
State: closed - Opened by yqzhishen 7 months ago
#171 - Support tension and voicing
Issue -
State: closed - Opened by yqzhishen 7 months ago
#170 - New variance parameter: voicing
Pull Request -
State: closed - Opened by yqzhishen 7 months ago
Labels: enhancement
#169 - New variance parameter: tension
Pull Request -
State: closed - Opened by yqzhishen 7 months ago
Labels: enhancement
#168 - Torch2.2 Error Variance
Issue -
State: closed - Opened by usasho 8 months ago
- 5 comments
#167 - Support OpenUtau yaml dictionary in diffsinger workflow
Pull Request -
State: open - Opened by oxygen-dioxide 8 months ago
#166 - Compatible with torch2.2
Pull Request -
State: open - Opened by autumn-2-net 8 months ago
#165 - Inference from Raw Input
Issue -
State: closed - Opened by Tox1cPhantom 8 months ago
- 5 comments
#162 - script to build openutau voicebank
Pull Request -
State: open - Opened by MLo7Ghinsan 8 months ago
- 1 comment
#161 - 关于breathiness的控制问题
Issue -
State: closed - Opened by mindrover 8 months ago
#160 - Error preventing preprocessing
Issue -
State: closed - Opened by agentasteriski 8 months ago
- 2 comments
#159 - Better than PL auto strategy selection
Pull Request -
State: closed - Opened by hrukalive 9 months ago
#158 - Different timbres from the same singer. seperated into unique speakers, all sound identical in a multi-speaker model
Issue -
State: closed - Opened by spicytigermeat 10 months ago
- 8 comments
#157 - A Tensorboard update issue in the case of multiple graphics cards.
Issue -
State: closed - Opened by KakaruHayate 10 months ago
- 2 comments
Labels: bug
#156 - Finish documentation for v2.2.0 release
Pull Request -
State: closed - Opened by yqzhishen 10 months ago
Labels: documentation
#155 - Batch evaluation inference scripts
Issue -
State: open - Opened by yqzhishen 10 months ago
- 1 comment
#153 - Update documentation formatting
Pull Request -
State: closed - Opened by hrukalive 11 months ago
Labels: documentation
#152 - Better normalization of variance parameters
Issue -
State: open - Opened by yqzhishen 11 months ago
#151 - Add gradient scale factor for duration predictor
Issue -
State: closed - Opened by yqzhishen 11 months ago
- 1 comment
#150 - Error exporting to ONNX
Issue -
State: closed - Opened by github-axel-boidin 11 months ago
- 3 comments
#149 - Add WORLD pitch estimators and F0 range as hyperparameters
Pull Request -
State: closed - Opened by UtaUtaUtau 11 months ago
- 10 comments
#148 - Multi-node batched validation and improvement on strategy selection
Pull Request -
State: closed - Opened by hrukalive 11 months ago
#147 - Does ds_variance.py align phoneme durations to notes like how it is done in OpenUTAU?
Issue -
State: closed - Opened by JieLuChen 12 months ago
- 1 comment
#146 - Fix parselmouth alignment
Pull Request -
State: closed - Opened by yxlllc 12 months ago
#145 - Apply for dataset
Issue -
State: closed - Opened by li-henan about 1 year ago
#144 - Fix change config
Pull Request -
State: closed - Opened by crlotwhite about 1 year ago
- 1 comment
#143 - Implement melody encoder and support glide input
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#142 - Melody encoder and ornaments modeling
Issue -
State: closed - Opened by yqzhishen about 1 year ago
- 4 comments
#141 - compatible with master version acoustic pre-train
Issue -
State: closed - Opened by nestyme about 1 year ago
- 2 comments
#140 - Error failed to render
Issue -
State: closed - Opened by gnloop about 1 year ago
- 8 comments
#139 - [MFA] Transform matrix for utterance 1-1 has bad dimension 40x112 versus feat dim 105
Issue -
State: closed - Opened by idootop about 1 year ago
#137 - running inference with acoustic model [question]
Issue -
State: closed - Opened by nestyme about 1 year ago
- 4 comments
#134 - On the problem of phoneme loss when using Opencpop data set to train automatic pitch model
Issue -
State: closed - Opened by Wangs-official about 1 year ago
- 2 comments
#133 - On the problem of missing three phonemes "ir", "E" and "En"
Issue -
State: closed - Opened by Wangs-official about 1 year ago
- 1 comment
#132 - Support training variance models from DS files
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#131 - Training variance models from DS files
Issue -
State: closed - Opened by yqzhishen about 1 year ago
#130 - run inference on my own checkpoint
Issue -
State: closed - Opened by nestyme about 1 year ago
- 4 comments
#129 - Re-implement shallow diffusion
Issue -
State: closed - Opened by yqzhishen about 1 year ago
#128 - Shallow diffusion and aux decoder
Pull Request -
State: closed - Opened by autumn-2-net about 1 year ago
#127 - Add objective evaluation metrics for duration predictor
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#126 - Make pauses / silence inside singing
Issue -
State: closed - Opened by MrDiplodocus about 1 year ago
- 2 comments
#125 - Support for complex LR scheduler configuration
Pull Request -
State: closed - Opened by hrukalive about 1 year ago
- 1 comment
Labels: enhancement
#124 - Conda install Diffsinger Error Data
Issue -
State: closed - Opened by usasho about 1 year ago
- 2 comments
#123 - Add support for objective evaluation metrics
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#122 - Support RMVPE for pitch extraction
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#121 - Can not export ONNX model
Issue -
State: closed - Opened by Katistic about 1 year ago
- 2 comments
#120 - support freezing model params
Pull Request -
State: closed - Opened by autumn-2-net about 1 year ago
#119 - Perform graceful exit on KeyboardInterrupt
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#118 - Support custom pitch extractor
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#117 - variance model onnx exporter
Issue -
State: closed - Opened by blueyred about 1 year ago
- 10 comments
#116 - Feature proposal: freeze specific parameters when finetuning
Issue -
State: closed - Opened by yqzhishen about 1 year ago
#115 - Remove several warning and better floating point representation on the progress bar
Pull Request -
State: closed - Opened by hrukalive about 1 year ago
#112 - Phoneme duration predictions / note slur issue
Issue -
State: closed - Opened by blueyred about 1 year ago
- 3 comments
#110 - Split note sequence data in variance_binarizer.py
Pull Request -
State: closed - Opened by blueyred about 1 year ago
#109 - How to use pretrained models?
Issue -
State: closed - Opened by med1844 about 1 year ago
- 8 comments
#108 - support finetune
Pull Request -
State: closed - Opened by autumn-2-net about 1 year ago
#107 - Feature proposal: finetuning from checkpoint
Issue -
State: closed - Opened by yqzhishen about 1 year ago
#106 - Finish documentation for version 2.0.0
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#105 - About Training Epochs error, valid, save model
Issue -
State: closed - Opened by NLPV2011 about 1 year ago
- 3 comments
#104 - Change variance retaking masks from zero inputs to zero embeddings
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#103 - 如何推理variance模型?
Issue -
State: closed - Opened by laiyoi about 1 year ago
- 10 comments
#102 - 创建config与训练时不匹配
Issue -
State: closed - Opened by laiyoi about 1 year ago
- 2 comments
#101 - Show split validation losses on TensorBoard
Pull Request -
State: closed - Opened by yqzhishen about 1 year ago
#98 - v2.0.0 release
Pull Request -
State: closed - Opened by yqzhishen over 1 year ago
#97 - Implement pitch expressiveness controlling mechanism
Pull Request -
State: closed - Opened by yqzhishen over 1 year ago
#96 - question about MIDI and F0
Issue -
State: closed - Opened by lvZic over 1 year ago
- 3 comments
#90 - New labeling scheme with universal dictionary support and variance models with local retaking
Pull Request -
State: closed - Opened by yqzhishen over 1 year ago
#74 - Tracing: deep refactoring of codebase and migration to new PyTorch & Lightning frameworks
Issue -
State: closed - Opened by yqzhishen over 1 year ago
- 10 comments
Labels: documentation, enhancement
#71 - 使用ddsp
Issue -
State: closed - Opened by detectiveli over 1 year ago
- 4 comments