Hello! It's great to have such an interesting and great project open source. However, this is my first time I've seen the operation of showing the "original(vocoder)" ,which is in the inference.ipynb.
Do you want to evaluate the effect of the vocoder,compare it with other converted voices, or do you have other purposes for the source speech processed with the vocoder(which is written as "original(vocoder)") in the inference.ipynb?
Yes, it was to compare the results from the vocoder reconstruction to identify whether the sound quality problem comes from the voice conversion model or the vocoder.
Hello! It's great to have such an interesting and great project open source. However, this is my first time I've seen the operation of showing the "original(vocoder)" ,which is in the inference.ipynb. Do you want to evaluate the effect of the vocoder,compare it with other converted voices, or do you have other purposes for the source speech processed with the vocoder(which is written as "original(vocoder)") in the inference.ipynb?