STTS | github repositories

Public repositories

1. Wikispeech Text-to-Speech

wikispeech-server
The main API for Wikispeech TTS
Source

pronlex
A library for lexicon databases written primarily in go and javascript
Source	Docs

symbolset
A repository for handling phonetic symbol sets and mappers/converters between different symbol sets and languages
Source	Docs

marytts
A MaryTTS fork adapted for Wikispeech
Source	MaryTTS master branch

lexdata
Lexicon data for Wikispeech initial setup
Source

This work was supported by the Swedish Post and Telecom Authority (PTS) through the grant "Wikispeech – en användargenererad talsyntes på Wikipedia" (2016–2017).

2. Wikispeech Speech Data Collector

wikispeech-annotator
Validation and annotation of recorded audio
Source

wikispeech-manuscriptor
Tools for creating manuscripts for TTS and ASR
Source

This work was supported by the Swedish Post and Telecom Authority (PTS) through the grant "Talresursinsamlaren – För ett tillgängligare Wikipedia genom Wikispeech" (2019–2021).

3. Other utilities

rbg2p
A library for rule based grapheme to phoneme conversion
Source	Docs

rbnf
A Go implementation of parts of ICU's spellout rules (RBNF) for numbers.
Source	Docs

decomp
A library for guessing compound boundaries of compound words, given a list of possible word parts
Source	Docs

wstats
A library for parsing wikimedia dump files
Source	Docs

translit
A package for transliteration between non-Latin scripts into Latin.
Source