search

modelscope / 3D-Speaker

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
Apache License 2.0
1.07k stars 93 forks source link

[BUG] 提fbank的频率和重采样之后的频率不一致 #40

Closed cdliang11 closed 9 months ago

cdliang11 commented 9 months ago

https://github.com/alibaba-damo-academy/3D-Speaker/blob/b537e3734bc502529bbdb921dca784cb9f67b1b5/speakerlab/bin/infer_sv.py#L165-L176

提fbank的频率始终为16kHz，应该等于重采样之后的频率

yfchenlucky commented 9 months ago

为什么会不一致？代码中没有重采样，只是选择单通道wav。可以再具体描述一下您遇到的问题吗？

cdliang11 commented 9 months ago

为什么会不一致？代码中没有重采样，只是选择单通道wav。可以再具体描述一下您遇到的问题吗？

嗷嗷，是我看错，是固定16k采样