test.py

import torchaudio
import torch
import torch.nn as nn
import numpy as np
from functions import *
from unet import UNet

"""
model = UNet()
model_state_dict = torch.load("huggingface/model.pth", map_location="cpu")
model.load_state_dict(model_state_dict["model_state_dict"])
print("# of trainable parameters =", sum(p.numel() for p in model.parameters() if p.requires_grad))

audio = load_audio("huggingface/p232_001.wav")
enhanced = predict("huggingface/p232_001.wav", model)
print(enhanced.shape)"""
string = "C:/Users/durim/Documents/KTH/Master_År2/DT2119-SSR/project_feature_extraction.ipynb"
print("/".join(string.split("/")[:-1]))