[Help]: Performance Inferior to Demo Showcase in terms of "FACodec: Voice Conversion Samples"

[zyy-fc]

Problem Overview

I download the audios from the "FACodec: Voice Conversion Samples" and I use the python script shown in FACodec-README with pretrained model "FACodecEncoderV2/FACodecDecoderV2", but the voice conversion is not as good as the demo showcase or the results in https://huggingface.co/spaces/amphion/naturalspeech3_facodec

audio files is here: audio files "1_female_recon.wav" is the voice conversion audio by myself, "1_female_recon_huggingface.wav" is from https://huggingface.co/spaces/amphion/naturalspeech3_facodec

[zyy-fc]

Another question: the difference between FACodecDecoderV2 and FACodecRedecoder is ?