MaryTTS - Revision history

Thorsten: Added category project.

2021-11-16T21:57:17Z

Added category project.

← Older revision		Revision as of 23:57, 16 November 2021
Line 58:		Line 58:
	<references />		<references />
	[[Category:TTS]]		[[Category:TTS]]
			[[Category:Project]]

Thorsten: Added link to reference phrases.

2021-11-13T16:59:16Z

Added link to reference phrases.

← Older revision		Revision as of 18:59, 13 November 2021
Line 43:		Line 43:

	== Performance ==		== Performance ==
			To be compareable for performance we should use [[MOS TTS multilanguage reference phrases\|identical phrases for testing purposes]].

	==== Voice: dfki-spike-hsmm en_GB ====		==== Voice: dfki-spike-hsmm en_GB ====

Florian: Added HTTP REST API note

2021-11-13T13:34:00Z

Added HTTP REST API note

← Older revision		Revision as of 15:34, 13 November 2021
Line 15:		Line 15:
	* Language support is very good: German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, Turkish and more		* Language support is very good: German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, Turkish and more
	*Pronunciation of times, dates, temperatures etc. can be very good. MaryTTS uses an extensive, handcrafted set of rules (and statistics) to handle this.<ref>http://mary.dfki.de/documentation/overview.html</ref>		*Pronunciation of times, dates, temperatures etc. can be very good. MaryTTS uses an extensive, handcrafted set of rules (and statistics) to handle this.<ref>http://mary.dfki.de/documentation/overview.html</ref>
			*MaryTTS is server-based meaning it offers a HTTP REST API out-of-the-box to synthesize text

	== Models ==		== Models ==

Florian: Smaller format fix

2021-11-13T12:54:54Z

Smaller format fix

← Older revision		Revision as of 14:54, 13 November 2021
Line 42:		Line 42:

	== Performance ==		== Performance ==
	==== ~~Mary-TTS -~~ Voice: dfki-spike-hsmm en_GB ====		==== Voice: dfki-spike-hsmm en_GB ====

	* Test system: Raspberry Pi4 4GB		* Test system: Raspberry Pi4 4GB

Florian: Model links, releases, more info

2021-11-13T12:45:40Z

Model links, releases, more info

← Older revision		Revision as of 14:45, 13 November 2021
Line 17:		Line 17:

	== Models ==		== Models ==
	[~~TBD~~]		Voice models can be downloaded via script from inside the release version or using these links:

			* [https://github.com/marytts/voice-bits1-hsmm/releases bits1-hsmm] - A female German hidden semi-Markov model voice
			* [https://github.com/marytts/voice-bits3-hsmm/releases/ bits3-hsmm] - A male German hidden semi-Markov model voice
			* [https://github.com/marytts/voice-cmu-slt-hsmm/ voice-cmu-slt-hsmm] (included) - A female US English hidden semi-Markov model voice
			* [https://github.com/marytts/voice-cmu-bdl-hsmm/releases/ cmu-bdl-hsmm] - A male US English hidden semi-Markov model voice
			* [https://github.com/marytts/voice-dfki-spike-hsmm/releases/ dfki-spike-hsmm] - A male British English hidden semi-Markov model voice
			* [https://github.com/marytts/voice-dfki-prudence-hsmm/releases/ dfki-prudence-hsmm] - A female British English hidden semi-Markov model voice
			* [https://github.com/marytts/voice-upmc-jessica-hsmm/releases/ upmc-jessica-hsmm] - A female French hidden semi-Markov model voice
			* ...

			[UNDER CONSTRUCTION]

	== Installation ==		== Installation ==
	Installation is super easy:		Installation is super easy:

	* Install Java 8 or 11		* Install Java 8 or 11 (Debian: 'sudo apt-get install openjdk-11-jdk-headless')
	* Download the release ZIP file		* Download the release ZIP file: [https://github.com/marytts/marytts/releases v5.2 official] or [https://github.com/fquirin/marytts/releases v6.0 snpashot]
	* Extract and start the server		* Extract the ZIP and start the server (run scripts are in 'marytts\bin')

	By default you can access the server in your browser via: http://localhost:59125/		By default you can access the server in your browser via: http://localhost:59125/
Line 31:		Line 42:

	== Performance ==		== Performance ==
	~~[TBD]~~

	==== Mary-TTS - Voice: dfki-spike-hsmm en_GB ====		==== Mary-TTS - Voice: dfki-spike-hsmm en_GB ====
	~~Test system: Raspberry Pi4 4GB~~

	Sentence: "Hello this is a test"		* Test system: Raspberry Pi4 4GB
			* Sentence: "Hello this is a test"
			* Run-time: 0.33 s
			* Real-time-factor: 0.19

	~~Run-time: 0~~.~~33 s~~		...

	~~Real-time-factor: 0.19~~		[UNDER CONSTRUCTION]

	<references />		<references />
	[[Category:TTS]]		[[Category:TTS]]

Florian: Performance metrik

2021-11-13T12:14:47Z

Performance metrik

@@ Line 32: / Line 32: @@
 == Performance ==
 [TBD]
 <references />
 [[Category:TTS]]

Florian: Added pronunciation advantage

2021-11-13T12:12:43Z

Added pronunciation advantage

← Older revision		Revision as of 14:12, 13 November 2021
Line 14:		Line 14:
	* Installation is super easy and it runs on Windows, Mac and Linux (every system that can install Java 8)		* Installation is super easy and it runs on Windows, Mac and Linux (every system that can install Java 8)
	* Language support is very good: German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, Turkish and more		* Language support is very good: German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, Turkish and more
			*Pronunciation of times, dates, temperatures etc. can be very good. MaryTTS uses an extensive, handcrafted set of rules (and statistics) to handle this.<ref>http://mary.dfki.de/documentation/overview.html</ref>

	== Models ==		== Models ==

Florian: Set category

2021-11-13T12:06:02Z

Set category

← Older revision		Revision as of 14:06, 13 November 2021
Line 31:		Line 31:
	== Performance ==		== Performance ==
	[TBD]		[TBD]
			<references />
			[[Category:TTS]]

Florian: Created MaryTTS page

2021-11-13T12:02:05Z

Created MaryTTS page

New page

== What is MaryTTS? ==
[http://mary.dfki.de/ Mary ('''M'''odular '''A'''rchitecture for '''R'''esearch in s'''Y'''ynthesis) Text-to-Speech] is an open-source (GNU LGPL license<ref>https://github.com/marytts/marytts/blob/master/LICENSE.md</ref>), multilingual Text-to-Speech Synthesis platform '''written in Java'''. It was originally developed as a collaborative project of [http://www.dfki.de/web DFKI’s] Language Technology Lab and the [http://www.coli.uni-saarland.de/groups/WB/Phonetics/ Institute of Phonetics] at Saarland University, Germany. It is now maintained by the Multimodal Speech Processing Group in the [https://www.mmci.uni-saarland.de/ Cluster of Excellence MMCI] and DFKI.<ref>http://mary.dfki.de/</ref>

MaryTTS has been around for a very! long time. Version 3.0 even dates back to 2006, long before Deep Learning was a broadly known term and the last official release was version 5.2 in 2016<ref>http://mary.dfki.de/download/index.html</ref>. The system uses [[wikipedia:Speech_synthesis#Unit_selection_synthesis|unit selection]] and [[wikipedia:Hidden_Markov_model|HMM]]-based techniques to build voices (today probably called AI, back then called statistics ^^). If you want to learn more about the architecture check out the [http://mary.dfki.de/documentation/index.html official documentation].

There is still activity on the GitHub page and internally there has been some major code refactoring but it is currently unclear if there will ever be another release version. There has been an unofficial snapshot release for the SEPIA Framework which runs stable on Java 11 but should be considered experimental: [https://github.com/fquirin/marytts/releases MaryTTS 6.0 snapshot] ([https://hub.docker.com/r/sepia/marytts Docker container]).

== Advantages of MaryTTS ==
MaryTTS has certain advantages compared to modern Deep Learning systems or classical, synthetic engines like [[eSpeak]]:

* The quality of the voice depends strongly on the model but can be surprisingly good, not state-of-the-art but much better than a synthetic voice.
* Audio generation is very fast and ranges from 0.2 to 0.5 [[Real-time-factor|RTF]] on a Raspberry Pi 4 depending on the selected voice<ref>https://b07z.net/downloads/tts.html</ref> meaning it can actually be used on edge devices.
* RAM consumption is moderate but you should probably reserve around 256-512 MB.
* Installation is super easy and it runs on Windows, Mac and Linux (every system that can install Java 8)
* Language support is very good: German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, Turkish and more

== Models ==
[TBD]

== Installation ==
Installation is super easy:

* Install Java 8 or 11
* Download the release ZIP file
* Extract and start the server

By default you can access the server in your browser via: http://localhost:59125/

In a production system you might want to run MaryTTS behind a [[wikipedia:Reverse_proxy|reverse proxy]] (like Nginx or Apache) to [https://github.com/SEPIA-Framework/sepia-assist-server/blob/master/Xtensions/TTS/marytts/INSTALL.md#solving-cors-problems avoid CORS issues].

== Performance ==
[TBD]