R9y9 Nnsvs Versions Save

Full Changelog: https://github.com/nnsvs/nnsvs/compare/v0.1.0...v0.1.1

What's Changed

• [ICASSP 2023] Dev update by @r9y9 in https://github.com/nnsvs/nnsvs/pull/147
• Add recipes for reproducing experiments reported in our NNSVS paper by @r9y9 in https://github.com/nnsvs/nnsvs/pull/151
• Remove recipe for no longer available data by @r9y9 in https://github.com/nnsvs/nnsvs/pull/152
• Add train_acoustic entry point in setup.py by @r9y9 in https://github.com/nnsvs/nnsvs/pull/155
• Remove vib_model and vib_flag_model from multi-stream models by @r9y9 in https://github.com/nnsvs/nnsvs/pull/156
• Fix the official URI of natsume_singing by @taroushirani in https://github.com/nnsvs/nnsvs/pull/158
• Fix config tests to cover untested acoustic model configs by @r9y9 in https://github.com/nnsvs/nnsvs/pull/159
• Replace duplicated use_harvest option by f0_extractor by @taroushirani in https://github.com/nnsvs/nnsvs/pull/160
• Fix train/dev/test split for Namine Ritsu's database by @r9y9 in https://github.com/nnsvs/nnsvs/pull/162
• Add recipe-level support for hn-uSFGAN and SiFi-GAN by @r9y9 in https://github.com/nnsvs/nnsvs/pull/157
• Add support for mcep-based aperiodicity parametrization by @r9y9 in https://github.com/nnsvs/nnsvs/pull/163
• Add guide for training DiffSinger with NNSVS's data created by stage 0 by @r9y9 in https://github.com/nnsvs/nnsvs/pull/164
• Implement has_residual_lf0_prediction method to the base class by @r9y9 in https://github.com/nnsvs/nnsvs/pull/165
• Fix oniku_kurumi_utagoe_db to use run_common_steps_dev.sh by @taroushirani in https://github.com/nnsvs/nnsvs/pull/166
• Remove hardcoded num_mels=80 and support arbitrary values by @r9y9 in https://github.com/nnsvs/nnsvs/pull/168
• Performance improvements for training acoustic models by @r9y9 in https://github.com/nnsvs/nnsvs/pull/170
• Fix MDN-based multi-stream models by @r9y9 in https://github.com/nnsvs/nnsvs/pull/172
• Expose initial value parameter for autoregressive decoder impl by @r9y9 in https://github.com/nnsvs/nnsvs/pull/173
• Deprecate unused option and add one more option to multi-stream models by @r9y9 in https://github.com/nnsvs/nnsvs/pull/174
• Support diffusion-based acoustic models by @r9y9 in https://github.com/nnsvs/nnsvs/pull/175
• preprocess: Add workaround for out-liers by @r9y9 in https://github.com/nnsvs/nnsvs/pull/176
• Add recipes for the Opencpop corpus by @r9y9 in https://github.com/nnsvs/nnsvs/pull/177
• Updated enunu2nnsvs.py to add main() by @oatsu-gh in https://github.com/nnsvs/nnsvs/pull/182
• Internal refactoring for svs.py and gen.py to make NNSVS more extensible by @r9y9 in https://github.com/nnsvs/nnsvs/pull/186
• Change not to use tempfile to avoid PermissionError in WIndows by @taroushirani in https://github.com/nnsvs/nnsvs/pull/190
• Fix CI related to matplotlib by @r9y9 in https://github.com/nnsvs/nnsvs/pull/192
• Add check for a short and single segment by @taroushirani in https://github.com/nnsvs/nnsvs/pull/193
• Update dependencies to support Python 3.10 and 3.11 by @r9y9 in https://github.com/nnsvs/nnsvs/pull/197

Full Changelog: https://github.com/nnsvs/nnsvs/compare/v0.0.3...v0.1.0

What's Changed

• Fix wrong database name. by @taroushirani in https://github.com/nnsvs/nnsvs/pull/102
• Merge dev branch to master by @r9y9 in https://github.com/nnsvs/nnsvs/pull/109
• Fix Conv1dResNet bugs and add tests to prevent future unintentional bugs by @r9y9 in https://github.com/nnsvs/nnsvs/pull/111
• Refactor model.py: split it into two modules by @r9y9 in https://github.com/nnsvs/nnsvs/pull/113
• Add nn.Dropout for MDN by @r9y9 in https://github.com/nnsvs/nnsvs/pull/114
• Doc updates: split model into generic and acoustic ones by @r9y9 in https://github.com/nnsvs/nnsvs/pull/115
• Add recipe test for CI by @r9y9 in https://github.com/nnsvs/nnsvs/pull/116
• Revert #114 and add tests for backward compatibility by @r9y9 in https://github.com/nnsvs/nnsvs/pull/117
• Add MDNv2: MDN (v1) + dropout by @r9y9 in https://github.com/nnsvs/nnsvs/pull/118
• Implement correct_vuv_by_phone using C-VUV_Voiced and C-VUV_Unvoiced flags by @r9y9 in https://github.com/nnsvs/nnsvs/pull/119
• Refactor recipes by @r9y9 in https://github.com/nnsvs/nnsvs/pull/120
• Add smoothing feature for post-filtering by @r9y9 in https://github.com/nnsvs/nnsvs/pull/121
• Add GV post-filter by @r9y9 in https://github.com/nnsvs/nnsvs/pull/122
• Add correct_vuv option for data pre-processing by @r9y9 in https://github.com/nnsvs/nnsvs/pull/123
• Add more docs by @r9y9 in https://github.com/nnsvs/nnsvs/pull/124
• Support training non-resf0 acoustic models with train_resf0.py by @r9y9 in https://github.com/nnsvs/nnsvs/pull/125
• Remove MultistreamParametricModel by @r9y9 in https://github.com/nnsvs/nnsvs/pull/126
• Add tests for low-pass filter and add a corner case handing by @r9y9 in https://github.com/nnsvs/nnsvs/pull/127
• Fix error when no dynamic features are used by @r9y9 in https://github.com/nnsvs/nnsvs/pull/128
• Revisit autoregressive models: refactor Tacotron code by @r9y9 in https://github.com/nnsvs/nnsvs/pull/129
• Update docs: moved nnsvs repo to https://github.com/nnsvs org by @r9y9 in https://github.com/nnsvs/nnsvs/pull/130
• Update README.md with correct documentation link by @nicolalandro in https://github.com/nnsvs/nnsvs/pull/131
• Fix Taco inference for reduction factor by @r9y9 in https://github.com/nnsvs/nnsvs/pull/132
• Fix NonAttentiveDecoder to output (B, T, C) by @r9y9 in https://github.com/nnsvs/nnsvs/pull/133
• Fix vocoder training for different feature extraction settings by @r9y9 in https://github.com/nnsvs/nnsvs/pull/134
• Add option to allow filtering of long segments by @r9y9 in https://github.com/nnsvs/nnsvs/pull/135
• Fix bug of corect_vuv option for pre-processing by @r9y9 in https://github.com/nnsvs/nnsvs/pull/136
• Fixes for scipy 1.9.0 by @r9y9 in https://github.com/nnsvs/nnsvs/pull/137
• Wrong device assignment of svs.py by @taroushirani in https://github.com/nnsvs/nnsvs/pull/138
• Dev update by @r9y9 in https://github.com/nnsvs/nnsvs/pull/139
• Fix bug of diff vibrato mode by @r9y9 in https://github.com/nnsvs/nnsvs/pull/141
• Enable codecov by @r9y9 in https://github.com/nnsvs/nnsvs/pull/143
• Add codecov ignore config by @r9y9 in https://github.com/nnsvs/nnsvs/pull/144

Full Changelog: https://github.com/nnsvs/nnsvs/compare/v0.0.2...v0.0.3

A version that should work with https://github.com/oatsu-gh/ENUNU/releases/tag/v0.4.0

New features

• Improved timings with MDN duration models #80
• Improved acoustic models with residual F0 prediction #76

Bug fixes

• numpy.linalg.LinAlgError in MDN models https://github.com/r9y9/nnsvs/issues/94

NOTE: Tagging a new release for upcoming huge refactoring and new features (could be with breaking API changes).

The initial version of nnsvs (with some experimental features like vibrato modeling and data augmentation). This version should be compatible with currently available tools around nnsvs (e.g., ENUNU). Hydra >=v1.0.0, <v1.2.0 is supported.

PyPi release is also available. So you can install the core library by pip install nnsvs.