Trained on a 11.38 min dataset of dirty and low quality audio with V2, RVMPE-Titan, 40 khz, 370 Epochs and batch size 8.
I might re-train it with a low-pass filter, since i really recommend putting it on (6000 hz or more in audacity or similar program) which i should have done in the first place but i thought it would work :/
I have datasets with the women as well and they will be uploaded it the coming days.

Samples:
https://www.weights.gg/models/clxgv1udd000s67dbh3hl296l
https://krakenfiles.com/profiles/beatledoh/files/Y2ZlNTA0ODMzZWM5YjRkNMqPviuE9bmucK7qHddsiio
Model: https://huggingface.co/Albinator/TrioOrientalBregaGuy/blob/main/TrioOrientalBregaGuy.zip
Some info about the group: https://www.youtube.com/watch?v=-5MpuNXaZNY

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/Albinator/TrioOrientalBregaGuy/blob/main/TrioOrientalBregaGuy.zip Hosted on Hugging Face