File tree Expand file tree Collapse file tree 3 files changed +3
-0
lines changed Expand file tree Collapse file tree 3 files changed +3
-0
lines changed Original file line number Diff line number Diff line change @@ -179,6 +179,7 @@ python train.py
179179- [ ] より良い歌声変換のためのNSFボコーダ
180180- [x] 非発話時のリアルタイム音声変換アーティファクトの修正(VADモデルの追加により対応)
181181- [x] ファインチューニング例のColabノートブック
182+ - [ ] Whisperをより高度な意味抽出器に置き換える
182183- [ ] 今後追加予定
183184
184185## 更新履歴🗒️
Original file line number Diff line number Diff line change @@ -164,6 +164,7 @@ where:
164164- [ ] 用于改善歌声转换的NSF歌声解码器
165165- [x] 实时变声脚本添加了VAD模型,避免没有说话时模型输出杂音
166166- [x] Google Colab 笔记本训练脚本以及样例
167+ - [ ] 替换whisper为更先进的语义内容提取器
167168- [ ] 更多待添加
168169
169170## 更新日志 🗒️
Original file line number Diff line number Diff line change @@ -173,6 +173,7 @@ where:
173173- [ ] NSF vocoder for better singing voice conversion
174174- [x] Fix real-time voice conversion artifact while not talking (done by adding a VAD model)
175175- [x] Colab Notebook for fine-tuning example
176+ - [ ] Replace whisper with more advanced linguistic content extractor
176177- [ ] More to be added
177178
178179## CHANGELOGS🗒️
You can’t perform that action at this time.
0 commit comments