forked from proycon/LaMachine
-
Notifications
You must be signed in to change notification settings - Fork 0
/
install-template.yml
114 lines (106 loc) · 9.03 KB
/
install-template.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
---
#################################################################################################################
# LaMachine Installation Manifest
#
# INSTRUCTIONS: Comment or remove categories/roles you do not want to install, dependencies will be automatically
# resolved even when not explicitly mentioned). Instead of editing this file, you can always add additional
# packages using lamachine-add once the system is installed.
#
# NOTE: ensure that all enabled roles are lined up with the same amount of spaces!
# (all hyphens must be vertically on the same column!)
# (don't use tabs)
#
################################################################################################################
- hosts: all
##1##
roles:
- lamachine-core ## The LaMachine core ##
#you always need this or nothing works; already includes Python 3
- python-core ## Core 3rd party scientific python packages ###
#(provides: numpy, scipy, pandas, matplotlib, scikit-learn, nltk, and more)
- java-core ## Java 8, Maven ##
- r-core ## R with core R packages ##
- nodejs-core ## Node.js with NPM ##
- extra-utils ## Extra command-line utilities useful for data science
#(provides: jq, ack, graphviz, gnuplot, glances, csvkit, xmlstarlet and a lot more)
- languagemachines-basic ## Generic & Dutch NLP tools written in C++ ##
#by the Language Machines Research group,
#Centre for Language and Speech Technology, Radboud University Nijmegen
#(provides: timbl, frog, ucto, folia, mbt, wopr, Colibri Core)
- languagemachines-python ## Python-based NLP tools and libraries and web applications/services ##
#by the Language Machines Research group,
#Centre for Language and Speech Technology, Radboud University Nijmegen
#(this includes pynlpl, pynlpl.formats.folia, CLAM, foliadocserve, FLAT, babelente)
- languagemachines-python-bindings ## Provides Python bindings to C++ software ##
#(provides python-ucto, python-frog, python-timbl, colibricore)
- nextflow ## Nextflow: Data-driven computational pipelines ##
- languagemachines-pipelines ## NLP Pipelines
#by the Language Machines Research group,
#(provides: aNtiLoPe, nederlab-pipeline)
- labirinto ## Labirinto provides the LaMachine Portal website, providing access to all installed webservices ##
#by the Language Machines Research group,
#Centre for Language and Speech Technology, Radboud University Nijmegen
- jupyter ## Jupyter Lab Environment, provides a powerful scripting IDE and terminal from the web-browser
#CAUTION: Allows arbitrary code execution over network!!! (password protected)
#Once installed, change the default password by running: lamachine-passwd lab
- python-course ## Python Course for the Humanities by Folgert Karsdorp et al. ##
# http://www.karsdorp.io/python-course/
#(requires jupyter)
# - cltl-vu-python ## Python software by the Computational Lexicology & Terminology Lab, VU Amsterdam
#(provides KafNafParserPy)
# - go-core ## Go compiler and standard library
# - piccl ## PICCL: Workflows for Post-OCR correction and normalisation and pseudo-modernisation of historical text. ##
# [2.2GB! - not supported on Mac OS X]
# (provides TICCL-Tools)
# - alpino ## ALPINO: Dependency parser for Dutch ##
# by Groningen University
# [1.6GB! - only supported on Debian/Ubuntu for now]
# - tscan ## T-Scan: Software for feature extraction for readability prediction ##
# by Utrecht University, Tilburg University & Radboud University
# [requires Alpino, so only supported on Debian/Ubuntu]
# - gecco ## Generic software for context-aware spelling correction ##
# Centre for Language and Speech Technology, Radboud University Nijmegen
# [Not supported on Mac OS X]
# - valkuil ## A Dutch Spelling corrector ##
# Centre for Language and Speech Technology, Radboud University Nijmegen
# [1.2GB! - Not supported on Mac OS X, requires at least 32GB RAM]
# - tensorflow ## Tensorflow Deep Learning Library for Python (by Google) ##
#(>250MB)
# - spacy ## spaCy is a library for advanced Natural Language Processing in Python and Cython ##
#(>500MB)
# - pytorch ## Deep-learning library for Python; also adds extras like FLAIR
# - kaldi ## Kaldi Automatic Speech Recognition Toolkit
#(>7GB !!!! - Not supported on Mac OS X)
# - corenlp ## Stanford CoreNLP (including all models)
#(>2GB)
# - freeling ## FreeLing, a multilingual open source language analysis tool suite
# by TALP Research Center, Universitat Politècnica de Catalunya
# - fy_nl_ASR ## Frisian-Dutch Speech Recognition system with webservice
#(>9GB !!!! - Not supported on Mac OS X)
#Relies on kaldi, another 7GB!!
#Authorization is required for this; ensure to
#set fame_user and fame_password in your LaMachine configuration
#contact [email protected] to request access
# - eng_ASR ## English Speech Recognition system with webservice
#(Not supported on Mac OS X)
#Relies on kaldi, another 7GB!!
# - moses ## Moses MT Decoder
# 7GB - Debian/Ubuntu only for now
# - oersetter ## Frisian<->Dutch Machine Translation system
# 2GB? - Debian/Ubuntu only for now
# - glem ## Lemmatiser for ancient greek
# ('Unraveling the Language of Perspective' project)
# Radboud University Nijmegen
# - phonetisaurus ## Grapheme to Phoneme conversion
#(not supported on Mac OS X)
# - g2pservice ## Grapheme to Phoneme conversion webservice
#(Authorization is required for this
#contact [email protected] to request access)
# - spotlight ## DBPedia Spotlight Named Entity recogniser and linker webservice
#(Models may take up several GB!, set the spotlight_languages variable
#to customise installed languages, we only ship a subset by default)
#(Needs to be started manually using 'spotlight' and a language code parameter)
# - fasttext ## Library for efficient text classification and representation learning
# NOTE: ensure that all enabled roles are lined up with the same amount of spaces!
# (all hyphens must be vertically on the same column!)
# (don't use tabs)