| language: | |
| - zh | |
| - en | |
| tags: | |
| - speech-synthesis | |
| - speech-to-speech | |
| - voice-conversion | |
| - pytorch | |
| - audio | |
| - chinese-tts | |
| - multi-speaker | |
| - convolution | |
| - encoder-decoder | |
| license: apache-2.0 | |
| datasets: | |
| - vctk | |
| library_name: pytorch | |
| # Convbased | |
| Gtihub: [https://github.com/Convbased/Convbased-Studio](https://github.com/Convbased/Convbased-Studio) | |
| 本项目专注于训练高质量的预训练底模，为语音转换任务提供强大的基础模型支持。 | |
| | 特征提取 | 声码器 | 采样率40k | 采样率48k | | |
| |-----------|--------|-----|-----| | |
| | contentvec | hifigannsf | ❌ | ✅ | | |
| | contentvec | sifigan | ❌ | ✅ | | |
| | spin | hifigannsf | ❌ | ✅ | | |
| | spin | sifigan | ❌ | ✅ | | |
| | chinese-hubert-base | hifigannsf | ❌ | ✅ | | |
| | chinese-hubert-base | sifigan | 🧱 | 🧱 | | |
| *致力于推进中文语音合成技术的发展，该底模已用于微调大部分模型于 [Convbased Studio](https://weights.chat/)* |