Releases: open-mmlab/Amphion
Releases · open-mmlab/Amphion
v0.1.1-alpha
What's Changed
- Update README.md by @eltociear in #41
- Add Demo Badges for SVC, TTA, and TTS by @RMSnow in #42
- Avoid Unbound Case of the download_root by @Adorable-Qin in #48
- Provide DEMO guide and express thanks by @Adorable-Qin in #55
- DiffWave Vocoder Added by @VocodexElysium in #56
- fix cosine_schedule_with_warmup for VALLE training by @HeCheng0625 in #52
- Added HifiTTS data preprocessor by @zyingt in #53
- fix a bug for vocoder inference by @VocodexElysium in #65
- Fix issues with while loop and trailing slash due to using sh instead of bash by @YasienDwieb in #60
- Fix Compatibility Issue with 'accelerate' Package by Reverting to Version 0.24.1 by @HarryHe11 in #73
- Add Resemblyzer for Speaker Similarity Evaluation & Bug fixes by @Merakist in #75
- Custom dataset & resume training recipe for SVC task by @viewfinder-annn in #72
- Fix bug for issue 76 (Import VariableSampler error) by @HeCheng0625 in #82
- Metrify RawNet3/Resemblyzer as Keywords & Update READMEs by @Merakist in #85
- remove redundant codes and update the function for fs2 feature by @ChenX17 in #86
- Adding Contribution Guideline for Amphion by @HarryHe11 in #92
- Check & Update PR Template by @HarryHe11 in #96
- Add issue templates by @yuantuo666 in #98
- Add WavLM speaker similarity for evaluation by @HeCheng0625 in #97
- Add AudioCaps dataset link for TTA by @HeCheng0625 in #100
- Delete utils/whisper.py by @HarryHe11 in #102
- Accelerate the calculation for CER metrics by @wsywsywsywsywsy979 in #104
- Fix bug for VITS resuming training by @lmxue in #108
- Add VALL-E pre-trained model trained on 6k-hour Librilight by @lmxue in #101
- Add preprocessing scripts for the librilight datasets by @HarryHe11 in #107
- Implement VitsSVC resume training / finetune feature by @viewfinder-annn in #95
- MFA Restructure & Environment Bug Fixes by @Merakist in #121
- Update VALL-E prompt examples by @lmxue in #126
- Update DiffComoSVC by @Lokshaw-Chau in #135
- Refine the multilingual front-end processing module by @lmxue in #137
- fix: G2P module fails to initialize #138 by @yuantuo666 in #139
- feat: support Docker installation by @yuantuo666 in #140
- Add support of visualization by @lmxue in #141
- Multi-speaker VITS & Hi-Fi TTS dataset structure by @zyingt in #131
New Contributors
- @eltociear made their first contribution in #41
- @zyingt made their first contribution in #53
- @YasienDwieb made their first contribution in #60
- @HarryHe11 made their first contribution in #73
- @Merakist made their first contribution in #75
- @yuantuo666 made their first contribution in #98
- @wsywsywsywsywsy979 made their first contribution in #104
- @Lokshaw-Chau made their first contribution in #135
Full Changelog: v0.1.0...v0.1.1-alpha
Contributors
YasienDwieb, eltociear, and 13 other contributors
Assets 2
v0.1.0
What's Changed
Full Changelog: https://github.com/open-mmlab/Amphion/commits/v0.1.0-alpha
What's Changed
- add core code of valle by @lmxue in #4
- Refactor G2P module and related process by @lmxue in #5
- Debug VITS for multi-speaker training by @lmxue in #6
- Fix bugs for extracting whisper features by @RMSnow in #7
- Resume for the SVC's vocalist pretrained ckpt by @RMSnow in #8
- Fix tts inference bugs by @lmxue in #13
- Fix bugs for FS2 inference on updated phone_extractor by @ChenX17 in #12
- Add dynamic batch size for valle by @HeCheng0625 in #17
- Revert "Add dynamic batch size for valle" by @lmxue in #18
- Add VitsSVC implementation by @viewfinder-annn in #14
- Better training recipes for evaluation and vocoder by @VocodexElysium in #20
- Add dynamic batch size for VALLE by @HeCheng0625 in #19
- Update pretrained tts models by @lmxue in #29
- update acoustic feature extractor of TTS by @lmxue in #28
- Improve the G2P LexiconModule of TTS by @treya-lin in #30
- Add workflow to check code format with black formatter by @BakerBunker in #27
- black format on changed files to make workflow work by @lmxue in #33
- split and process valid set by @lmxue in #25
- Refine Whisper and WeNet Contents Extractor by @Adorable-Qin in #32
- Fix VitsSVC model infer bug when using nsfhifigan as generator by @viewfinder-annn in #37
- Debug for issue 23 by @ChenX17 in #34
- Control the Diffusion SVC Inference Steps in Args by @RMSnow in #38
- Add NaturalSpeech2 by @HeCheng0625 in #35
- Amphion v0.1 Release by @RMSnow in #39
New Contributors
- @treya-lin made their first contribution in #30
- @BakerBunker made their first contribution in #27
Full Changelog: v0.1.0-alpha...v0.1.0
Contributors
BakerBunker, RMSnow, and 7 other contributors
Assets 2
v0.1.0-alpha
What's Changed
Full Changelog: https://github.com/open-mmlab/Amphion/commits/v0.1.0-alpha
Contributors
RMSnow and lmxue