RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI
hubert编码的数据，使用onnx推理出来前/后存在杂音
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 38.4k
- Forks
- 5.3k
- PR merge metrics
- No merged PRs in 30d
Description
我在使用onnx_inference_demo.py测试onnx的实时变声推理效果。
由于需要满足延迟小的要求，因此测试时会将读入的音频文件按照一片6400 pcm的大小切分。
然后循环送入demo中，但发现推理后，每片输出数据的开始和结尾处会存在杂音。
怀疑是hubert在对片段的前后部分编码时由于没有参考帧，所以编成了杂音。
我使用的编码器模型为vec-768-layer-12.onnx
使用的音色模型是用RVC自带的export_onnx.py导出的动态Onnx模型（参考isses1830解决）
请问是否有方法解决这个杂音问题？
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with onnx_inference_demo.py and reproduce the artifact using 6400-PCM chunks and vec-768-layer-12.onnx. Compare the chunk boundaries with the exported dynamic ONNX model from export_onnx.py; done means real-time inference no longer produces noise at the beginning or end of each output chunk.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100