vyraun

raise ValueError("DEPRECATED/FROZEN - see https://github.com/kastnerkyle/tools for the latest")

# License: BSD 3-clause
# Authors: Kyle Kastner
# Harvest, Cheaptrick, D4C, WORLD routines based on MATLAB code from M. Morise
# http://ml.cs.yamanashi.ac.jp/world/english/
# MGC code based on r9y9 (Ryuichi Yamamoto) MelGeneralizedCepstrums.jl
# Pieces also adapted from SPTK
from __future__ import division
import numpy as np

vyraun

# -*- coding: utf-8 -*-
# Authors: jfsantos, Kyle Kastner
import sys
import numpy as np
import wave
import scipy as sp
from scipy.io import wavfile


def segment_axis(a, length, overlap=0, axis=None, end='cut', endvalue=0):

vyraun

vyraun

import numpy as np
from scipy.misc import imread
from itertools import product


# https://www.mathworks.com/matlabcentral/fileexchange/36538-very-fast-mutual-information-betweentwo-images?focused=3869473&tab=function
def mutual_info(X, Y, levels=256):
    # example inputs are images, but it shouldn't matter
    X = X.astype("float32")
    Y = Y.astype("float32")

vyraun

Building custom layers in Keras

About Keras

Keras is currently one of the most commonly used deep learning libraries today. And part of the reason why it's so popular is its API. Keras was built as a high-level API for other deep learning libraries ie Keras as such does not perform low-level tensor operations, instead provides an interface to its backend which are built for such operations. This allows Keras to abstract a lot of the underlying details and allows the programmer to concentrate on the architecture of the model. Currently Keras supports Tensorflow, Theano and CNTK as its backends.

Let's see what I mean. Tensorflow is one of the backends used by Keras. Here's the code for MNIST classification in TensorFlow and Keras. Both models are nearly identical and applies to the same problem. But if you compare the codes you g

vyraun

def top_k_top_p_filtering(logits, top_k=0, top_p=0.0, filter_value=-float('Inf')):
    """ Filter a distribution of logits using top-k and/or nucleus (top-p) filtering
        Args:
            logits: logits distribution shape (..., vocabulary size)
            top_k >0: keep only top k tokens with highest probability (top-k filtering).
            top_p >0.0: keep the top tokens with cumulative probability >= top_p (nucleus filtering).
    """
    top_k = min(top_k, logits.size(-1))  # Safety check
    if top_k > 0:
        # Remove all tokens with a probability less than the last token of the top-k

vyraun

ffmpeg

Converting Audio into Different Formats / Sample Rates

Minimal example: transcode from MP3 to WMA:
ffmpeg -i input.mp3 output.wma

You can get the list of supported formats with:
ffmpeg -formats

Convert WAV to MP3, mix down to mono (use 1 audio channel), set bit rate to 64 kbps and sample rate to 22050 Hz:

vyraun

tmux cheatsheet

As configured in my dotfiles.

start new:

tmux

start new with session name:

vyraun

import torch
from pytorch_pretrained_bert import BertForMaskedLM, BertTokenizer
import random

# Requires pytorch_pretrained_bert: https://github.com/huggingface/pytorch-pretrained-BERT

# returns the probabilities over the vocabulary for the masked words in sent
def get_preds(sent):
    tokenized = bert_tokenizer.tokenize(sent)
    tokenized = ['[CLS]'] + ['[MASK]' if x == 'mask' else x for x in tokenized] + ['[SEP]']

vyraun