STTS | Wikispeech Text-to-Speech

Wikimedia's official information about the project: www.mediawiki.org/wiki/Wikispeech

1. Installation instructions

Standard installation

Standard installation (for advanced users). Please note that the sub-servers must be up and running before the main Wikispeech server can be started.

The main Wikispeech server

Sub-servers:

Symbolset (symbolset/mapping server) [from March, 2020]
Pronlex (lexicon server)
MaryTTS (TTS engine, adapted version for Wikispeech)
Mishkal (optional, required for Arabic vocalization)
Start the server by running: $ python interfaces/web/mishkal-webserver.py
AhoTTS-eu-Wikispeech (optional TTS engine for Basque, adapted version for Wikispeech)

Convenience scripts for running the full standard setup with all servers:

2. API documentation

When you have installed and started the Wikispeech server, you can find the API documentation in the URLs below. (Examples for server located on localhost, with default ports.)

Main API/Wikispeech server: http://localhost:10000

Sub-servers:

Symbolset server: http://localhost:8711 [from March, 2020]
Lexicon server: http://localhost:8787
Marytts: http://localhost:59125/documentation.html

3. Release notes

4. System requirements

There are few specific system requirements for the Wikispeech server. Below are rough estimates on requirements to run Wikispeech with the standard voices and lexicon databases. Please note that it may still work with lower performance than this, and for some situations, you may need more than this to run.

Disk space: ~5G (standad installation)

RAM: 4-8G

The following may also be worth to keep in mind:

Inherited system requirements from used software packages, such as MaryTTS, python, opus, flite, sqlite3, java, go, docker, etc
Recommended architecture: Linux 64-bit

Wikispeech has been tested for the following specific OSs:

Ubuntu 17.10
Ubuntu 16.04 LTS
Debian 8 (Jessie)

5. Adding new components/voices/languages to Wikispeech

At the moment, there is no comprehensive documentation available on how to build a new voice or a new language for Wikispeech.

If you want to contribute to Wikispeech, please consult with the Wikimedia team who will coordinate community based improvements. You can read more about how to contribute here: www.mediawiki.org/wiki/Wikispeech.

You are also welcome to contact us at stts.se/contact if you want.

5.1 Building voices for MaryTTS and Flite

For information on how to build voices for MaryTTS and Flite, follow the links below. Please note that Wikispeech still needs to be configured for the voices to work in the Wikispeech environment (see below).

MaryTTS
Flite

5.2 Symbol set

Documentation of the symbolset format

5.3 Lexicon data

Documentation of the Wikispeech lexicon file format

A lexicon file in this format can be imported using the lexserver API URL /admin/lex_import_page, or from the command line using importLex.

5.4 Configuring Wikispeech for a new voice/language

The wikispeech server is currently configured with a python source file "voice_config.py", containing two lists, textprocessor_configs and voice_configs. To add a new language, add entries for textprocessor and voice, similar to the examples below. Please note that the examples here use the MaryTTS adapter.

Textprocessor:
    {"name":"TEXTPROCESSOR_NAME", "lang":"MYLANGAUGE",
     "components":[
         {
             "module":"adapters.marytts_adapter",
             "call":"marytts_preproc",
             "mapper": {
                 "from":"LEXICON_SYMBOLSET",
                 "to":"MARYTTS_SYMBOLSET"
             },
         },
         {
             "module":"adapters.lexicon_client",
             "call":"lexLookup",
             "lexicon":"MY_LEXICON_NAME"
         }
     ]
    }

Voice:
    {
        "lang":"MYLANGUAGE",
        "name":"MARYTTS_VOICE_NAME",
        "engine":"marytts",
        "adapter":"adapters.marytts_adapter",
        "mapper": {
            "from":"LEXICON_SYMBOL_SET",
            "to":"MARYTTS_SYMBOL_SET"
            }
    }

6. More information

An UML diagram over the Wikispeech server: github.com/stts-se/wikispeech-server/wiki/uml/basic.png

Github repositories

Main repos

Forks from existing repos

Self-financed repos

A list of all STTS' public repositories on github: stts-se.github.io/repos

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