fauxneticien

# User Praat formant tracker with default settings
#
# Arguments
# input_file: Full file path to location of .wav file
# output_file: Full file path and file name, .csv file recommended
#
#
# Sample usage from command line (OS X)
# /Applications/Praat.app/Contents/MacOS/Praat --run "/Users/Nay/get_formants_as_csv.praat" "/Users/Nay/Desktop/sandboxes/b001_file01.wav" "/Users/Nay/Desktop/sandboxes/b001_file01.csv"
#

fauxneticien

#!/usr/bin/env Rscript

# Split a media file associated with an ELAN file according to some tier
#
# Dependencies: ffmpeg, tidyverse (R Package)
#
# Usage:   RScript split_media_by_eaf_tier.R eaf_file tier_name
# Example: RScript split_media_by_eaf_tier.R example.eaf tier_A

# Load packages, install 'tidyverse' (it includes both xml2 and stringr in it)

fauxneticien

sudo apt-get update
sudo apt-key adv --keyserver hkp://p80.pool.sks-keyservers.net:80 --recv-keys 58118E89F3A912897C070ADBF76221572C52609D
sudo apt-add-repository 'deb https://apt.dockerproject.org/repo ubuntu-xenial main'
sudo apt-get update
apt-cache policy docker-engine
sudo apt-get install -y docker-engine
docker info

fauxneticien

############################## 1. Set up ######################################

# Make sure you have the necessary packages installed (see section 2).

# The last number from the list URL for example 1045 for:
# https://app.alveo.edu.au/item_lists/1045
alveo_list_id <- 904

# Regex pattern to search for 'speaker16.wav$' means 'ending with speaker16.wav'
alveo_search_pattern <- "speaker16.wav$"

fauxneticien

#/bin/bash

export SEARCH_FOLDER=/git-repos/asr-daan/komnzo_text

time find "$SEARCH_FOLDER" -name "*.eaf" |
    parallel -j 4 '
        grep -v "^<?xml" {} |
        sed "s%<ANNOTATION_DOCUMENT \(.*\)>%<ANNOTATION_DOCUMENT \1 SRC=\"{}\">%g"
    ' |
    awk 'BEGIN{print "<?xml version=\"1.0\" encoding=\"UTF-8\"?><EAFS_DB>"}

fauxneticien

#!/usr/bin/python

# Usage: pass in a grammar from a text file, or define them chunk-by-chunk as following arguments
# python chunker.py < lexicon.txt "xml" $(cat grammar.txt)
# python chunker.py < lexicon.txt "json" "examples:{<text><translation>}" "headword:{<lx><ps><examples>*}"

import cStringIO, json, sys, xmltodict, xml.dom.minidom
from toolz.functoolz import pipe
from nltk.toolbox import ToolboxData
from xml.etree.ElementTree import ElementTree

fauxneticien

license: gpl-3.0
height: 480

fauxneticien

# Generates a script ~/init_users.sh, which when run
# adds 50 users who can log into the Docker image running rocker/verse
# https://hub.docker.com/r/rocker/verse/

library(purrr)
library(stringr)

install.packages("glue")
library(glue)

fauxneticien

/*
// Helper to split an initial object into a nested array
// by Mark Ellison <https://github.com/tyrannomark> mostly!

ecuder([x => x.split(" ")])("one two")
ecuder([x => x.split(" "), x => x.split("")])("one two")
ecuder([x => x.split(/\.\s?/), x => x.split(" "), x => x.split("")])("sentence one. sentence two")
*/

function ecuder(funcs_array, initial_obj) {

fauxneticien

# This is a tidyverse-friendly wrapper function for wrassp::mhsF0
#
# Usage:
#
# dir(path = ".", pattern = "*.wav", full.names = TRUE) %>% mhsF0_df
# dir(path = ".", pattern = "*.wav", full.names = TRUE) %>% mhsF0_df(beginTime = 1, gender = "f")
#
# For list of arguments to wrassp::mhsF0, see https://www.rdocumentation.org/packages/wrassp/versions/0.1.4/topics/mhsF0

mhsF0_df <- function(fileList, ...) {