kanara/onnx-voice-changer
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: add Kanara Technology credit section to all READMEs

Browse Source
This commit is contained in:
akukanara
2026-05-31 17:06:44 +07:00
Unverified
parent c169172c48
commit adf6dc2a24
5 changed files with 30 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/README.zh.md
+6
View File
@@ -163,3 +163,9 @@ python server.py --host 127.0.0.1 --port 8765 --device cuda
1. **滑动窗口上下文缓冲区:** 保持较短的音频历史缓冲区，以向模型提供所需的上下文帧，同时最小化输出音频延迟。
2. **卷积填充淡出:** 在输入片段中临时追加 120ms 的尾随静音填充，以避免 RVC 卷积步骤中固有的边缘淡入淡出异常。
3. **线性重采样:** 低开销的线性插值，可快速适应采样率。
---
## 🤝 鸣谢与贡献
* **由 [Kanara Technology](https://github.com/kanaratech) 用 ❤️ 制作**
* 基于 [ONNX Runtime](https://onnxruntime.ai/) 和 [Retrieval-based Voice Conversion (RVC)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)