RicherMans

ufw enable
ufw allow ssh
ufw allow 41335:60031/tcp # Or your v2ray kcp/udp port range
ufw allow 41335:60031/udp # Or your v2ray kcp/udp port range
ufw allow http
ufw allow https
ufw default deny incoming
ufw reload

RicherMans

import librosa
import scipy
import numpy as np


def cmc(y, sr, P=12, n_level=7, eps=1e-12, **kwargs):
    log_abs_power_cqt = np.log(
        np.abs(librosa.core.cqt(y=y, sr=sr, **kwargs))**2 + eps)
    cmc_levels = []
    for _ in range(n_level):

RicherMans

import numpy as np
import scipy
import matplotlib.pyplot as plt
import librosa


def lin(sr, n_fft, n_filter=128, fmin=0.0, fmax=None, dtype=np.float32):

    if fmax is None:
        fmax = float(sr) / 2

RicherMans

# @Author: richman
# @Date:   2018-03-15
# @Last Modified by:   richman
# @Last Modified time: 2018-03-30

if [[ $# < 1 ]]; then
    echo "Input .csv file .e.g balanced_train_segments.csv"
    exit
fi

RicherMans

# @Author: richman
# @Date:   2018-03-15
# @Last Modified by:   richman
# @Last Modified time: 2018-03-30

if [[ $# < 1 ]]; then
    echo "Input .csv file .e.g balanced_train_segments.csv"
    exit
fi

RicherMans

import torch
import torch.nn as nn
import torch.nn.functional as F


class MovingAvgNorm(nn.Module):
    """
    Calculates multiple moving average estiamtes given a kernel_size
    Similar to kaldi's apply-cmvn-sliding 
    """

RicherMans

import h5py
import numpy as np
from tqdm import tqdm

indices = list(range(100000))
rand_index = np.random.permutation(len(indices)).astype(str)
BATCH_SIZE = 128


def batch_gen():

RicherMans

from sklearn.mixture import GaussianMixture
import h5py
import fire
import numpy as np
import pandas as pd
from pypeln import thread as pr
from joblib import dump, load
from tqdm import tqdm

RicherMans

RicherMans