Some question about features KNN about knn-vc HOT 2 CLOSED

Hi @huutuongtu , yep that might work quite well! It should be fairly easy to experiment with that without any retraining as well, since all you need to do is pass new arguments to the y_seq: Tensor, matching_set: Tensor, synth_set: Tensor arguments of the match(...) function. Namely, you can keep the synth_set the default WavLM SSL features, but for the y_seq (query sequence) and matching_set (matching set) you can use the features from ASR fine-tuned WavLM.

If you try it out, I'd be interested to hear how it goes!

from knn-vc.

Hmm, I've tried using the pretrained ASR model wav2vec2-base-100h from Facebook and wavlm patrickvonplaten/wavlm-libri-clean-100h-base-plus, but the results aren't satisfactory (too noisy) :D. Perhaps retraining the vocoder with semantic features could improve the results. Here is the link to some samples: https://drive.google.com/drive/folders/19lVYEi20iOzhxDXv1fiXA0PXtlvV7aHx?usp=sharing

from knn-vc.