Version 0.6.1

What's Changed

• Add LibriTTS-R recipe by @ShigekiKarita in #414
• Update version and add ci for newest pytorch by @kan-bayashi in #418

New Contributors

• @ShigekiKarita made their first contribution in #414

Full Changelog: v0.6.0...v.0.6.1

Version 0.6.0

What's Changed

• temporary fixed protobuf version by @kan-bayashi in #366
• Fix #367 by @kan-bayashi in #369
• CVSS_C Recipe by @ftshijt in #386
• support VQ-VAE and discrete symbol models by @kan-bayashi in #387
• use isort by @kan-bayashi in #389
• Apply new black ✨ 🍰 ✨ by @kan-bayashi in #390
• Hubert-discrete symbol-based HiFiGAN with duration predictor by @ftshijt in #388
• Fixes to discrete-symbol-based vocoder by @ftshijt in #394
• fix ci by @kan-bayashi in #398
• add singing vocoder and update f0 & excitation input feats by @DrWelles in #391
• fix norm issue by @kan-bayashi in #409
• fix pyreaper installation by @kan-bayashi in #411
• fix the case when segments has different #lines from wav.scp by @kan-bayashi in #413

New Contributors

• @DrWelles made their first contribution in #391

Full Changelog: v0.5.5...v0.6.0

Version 0.5.5

What's Changed

• add recipe for kiritan & ofuton_p_utagoe db (singing voice synthesis) by @PeterGuoRuc in #330
• Add recipe for Opencpop by @ftshijt in #332
• add causal option for HiFiGAN by @chomeyama in #326
• Fix HiFiGAN compatibility by @kan-bayashi in #334
• add recipe for natsume (singing voice synthesis) by @PeterGuoRuc in #336
• Update readme with pre-trained models on svs and demonstration by @ftshijt in #335
• Add recipes and pretrained models for CSD (Korean&English) and KiSIng (Mandarin) databases by @ftshijt in #342
• Add new recipe PJS (singing voice synthesis) by @A-Quarter-Mile in #347
• add no7singing training by @frankxu2004 in #349
• Add icelandic by @G-Thor in #354
• add tag_or_url for download_pretrained_model by @roholazandie in #361
• Apply black by @kan-bayashi in #362
• Update to v0.5.5 by @kan-bayashi in #363

New Contributors

• @PeterGuoRuc made their first contribution in #330
• @chomeyama made their first contribution in #326
• @A-Quarter-Mile made their first contribution in #347
• @frankxu2004 made their first contribution in #349
• @G-Thor made their first contribution in #354
• @roholazandie made their first contribution in #361

Full Changelog: v0.5.4...v0.5.5

Version 0.5.4

What's Changed

• add kss recipe by @windtoker in #306
• Fix a noise shape of StyleMelGANGenerator to export ONNX model by @c-bata in #312
• add recipe for oniku_kurumi_utagoe db (singing voice synthesis) by @ftshijt in #323
• update documentation and correct the download link for oniku-db by @ftshijt in #324
• Fix an error librosa update by @kan-bayashi in #327
• Add pytorch 1.10.x CI by @kan-bayashi in #328

New Contributors

• @windtoker made their first contribution in #306
• @c-bata made their first contribution in #312
• @ftshijt made their first contribution in #323

Full Changelog: v0.5.3...v0.5.4

Version 0.5.3

• Added pretrained models.

Version 0.5.2

• Added pretrained models
• Fixed typo
• Introduced filelock to prevent from duplicated download

Version 0.5.1

• Support normalize-before option in decoding
• Support log_base option in preprocessing
• Update pre-trained models

Version 0.5.0

• Support HiFiGAN
• Support StyleMelGAN
• Refactored

Version 0.4.8

• Support Pytorch 1.7
• Add JSSS recipe
• Support the case where wav.scp and segments have a different number of lines

Version 0.4.6

• Minor fix of pretrained model save directory