Utilizes ONNX Runtime for audio denoising.
- Now support:
- It is not recommended to apply dynamic quantization to ZipEnhancer, as it significantly slows down inference due to the increased computational load.
- This end-to-end version includes internal
STFT/ISTFT
processing. Input noisy audio; output is crystal clear. - Download
- See more -> https://dakeqq.github.io/overview/
- 现在支持:
- 不建议对 ZipEnhancer 应用动态量化,因为这会由于计算负载的增加而显著减慢推理速度。
- 这个端到端的版本包含
STFT/ISTFT
处理。简单的输入噪声音频,输出则是清澈明了的音频。 - 下载
- See more -> https://dakeqq.github.io/overview/
OS | Device | Backend | Model | Real-Time Factor ( Chunk_Size: 4000 or 250ms ) |
---|---|---|---|---|
Ubuntu-24.04 | Desktop | CPU i3-12300 |
ZipEnhancer f32 |
0.32 |
macOS 15 | MacBook Air | CPU M3 |
ZipEnhancer f32 |
0.25 |
Ubuntu-24.04 | Desktop | CPU i3-12300 |
GTCRN f32 |
0.0036 |
macOS 15 | MacBook Air | CPU M3 |
GTCRN f32 |
0.0013 ~ 0.0019 |