Welsh Language Technology
Want to know more about Welsh language technology? Helo Blod can help.
Whether your business needs a Welsh digital spelling and grammar checker or you’re looking to develop new software, resources and services, our list of Welsh and bilingual resources is the perfect place to start.
It's a live list - help Helo Blod keep it up to date by letting us know about any mistakes or things you think we should add.
Do you use Microsoft 365? The Welsh language interface is available free of charge.
This collection of office programs is free of charge but what's even better is that they're available in Welsh!
Ever come across an unfamiliar word when reading a Welsh web page? Move the mouse over that word and Vocab will show you the translation.
Use more Welsh in your everyday life with this open source e-mail, news feed, chat and calendar app.
Do you want to install a Welsh interface on your computer but don't know where to start? Watch this collection of videos which are easy to follow and show you exactly how to go about it.
Thanks to this interactive Welsh map, you'll never need to feel lost again! The place-names all appear in Welsh and you can embed the map on your own websites too.
Do you or your company offer a service in English only? Perhaps Linguaskin can help you offer it in Welsh too.
An extension to the Chrome browser that highlights Welsh words so you can understand them more easily if you're learning Welsh.
Learning or improving your Welsh? Are your children in Welsh medium education? Do you help them with their homework? Or are you just searching for peace of mind that every t c p has changed to d g b in the correct place? Cysgliad can help. And it’s available for free.
Fancy trying it? Cysgliad’s FREE LICENSE for individuals, schools and organizations employing 10 people or less is now available with the support of the Welsh Government.
What’s in Cysgliad?
- Don't worry about mistakes, let Cysill correct any language errors and help with the mutations!
- Can't quite remember what the Welsh word for "computer" is? Is it a masculine of feminine noun? Search through Cysgeir for the answer.
Term base, style guides and all kinds of other useful resources to help with translation and creating original content in Welsh.
If you are writing about race and ethnicity and want to make sure you use the most appropriate terms and words, this is the place to go. There are LGBTQ+ and COVID glossaries here too.
CorCenCC - National Corpus of Contemporary Welsh
CorCenCC's electronic database contains 10 million Welsh words. You can see examples of words within various texts, rather than definitions. //Eager to know more about how CorCenCC puts this database together? Good news - all the documents related to the project are available for free here.
- This is the vocabulary behind the CorCenCC language technology resources
- A collection of natural language processing tools Python for Welsh, which includes a text segmenter, sentence splitter, tokenizer and parts of speech tagger
- Semantic tagger which is based on Lancaster University's rules
- Bant à ti: tag your parts of speech Welsh.
- Basically, everyone likes a Stemmer. Here's a Python one that uses Porter's algorithm adapted for Welsh
- Various text tools - Word locator, word frequency detector and other text tools.
Bangor University's Welsh-English sentence aligner
Here is a resource for the translators among us; a program that aligns equivalent Welsh and English texts at sentence level. Remember your translation memories and feed in DMX with this handy tool.
A generative AI tool that's growing in its ability to process Welsh.
AI partnership between Wales and Catalonia.
Another generative AI tool that's starting to process Welsh.
Domain specific machine translators
If you're a translator who specialises in Health and Care or Legislation, try these subject specific machine translators.
Take a look at Hedyn to find out which WordPress plugins and themes are available in Welsh.
University of South Wales Welsh Natural Language Toolkit (WNLT)
Do you love text analysis? Who doesn't? This pack includes a word splitter, a parts of speech tagger and a stemmer for the Welsh language. You can also use it to analyse what's being said in social media.
Flexi Term Cymraeg: Cardiff University's Welsh term finder
So you know how to run Java script – that’s a gold star from us! Why not test your skills and try FlexiTerm? Software that automatically highlights possible terms in Welsh texts.
Interested in translation and looking for old school locally-installable statistical machine translation software? Ta-da... you've found one!
A new approach to creating bilingual content without relying solely on translation.
An easy way to subtitle videos in Welsh. You'll still need to proofread the text!
If you, or your children, are learning to code with the BBC Micro:bit at school, here are extremely handy resources.
Guidance on simultaneous interpretation on Teams
Here's pdf and video guidance on how to set up and use simultaneous interpretation on Teams.
The Welsh Government's Welsh Language Technology Action Plan
The world of technology is moving quickly - this is a 2018 plan to make sure the Welsh language keeps up in the world of technology.
Welsh Language Technology Action Plan: Final Report 2018 to 2024
Welsh Government work between 2018 and 2024 to help develop Welsh language technology infrastructure.
The gift everyone has been waiting for - a hundred thousand and more Welsh articles, and more being published every day.
Y Pod - Welsh language podcast directory
Fancy listening to a Welsh podcast but don't know where to start? There's something for everyone at Y Pod.
Welsh National Language Technologies Portal
Why not introduce the Welsh language to your digital project? There is something here for everyone who likes Welsh technology.
You can rely on the Welsh Hacio'r Iaith language hacking community to discuss developments in the Welsh language digital world.
Would you like more Welsh content on your phone? Look through this list of iOS and Android apps, which are either in Welsh or contain an element of Welsh, and it's then just a small matter of downloading the apps.
Bangor University's Welsh language technology portal
A website with almost as many Welsh tech links as Helo Blod!
Microsoft's list of Welsh technological terms and style guide
Consistently using the right terms is important when localizing software. Set the language to 'Welsh' and away you go! Oh, and there's also a detailed style guide to helps translators and localizers too.
Bangor University's dictionary portal
Lots of lists to help with everything! From the most common Welsh words to lists of spelling, pronunciation and all kinds of themes. It's all available in one easy place.
Is there another word for Thesaurus? I wonder...
Welsh programs and apps.
Remember that you can use WordPress in Welsh as you develop a website or blog. You could even add a bit of Cymraeg with Hedyn’s handy list of Welsh plugins and themes: Hedyn's Welsh plugins for WordPress
A program available in several languages - including Welsh. Scratch makes it easy for kids (or adults) to learn to code. You can learn how to program interactive games and animations.
A predictive keyboard that learns and adapts to the way you write in Welsh and English at the same time.
Byd Term Cymru's downloadable terms
If you're looking for a term base to use in translation memory, it's worth downloading the standardised TermCymru base.
BydTermCymru's list of placenames of the world
From Emiradau Arabaidd Unedig to Wcráin, here are Welsh lists of place names around the world.
BydTermCymru's list of placenames in Wales
The Welsh Government translation service's list of Welsh place names.
Standardised Welsh Place-names - Welsh Language Commissioner
The Welsh Language Commissioner's list of Welsh place names.
Technocamps runs Welsh coding workshops.
This is where procurement and commercial communities can learn from and support each other.
Exploration, analysis, learning, and referencing of the Welsh language - all in one handy website.
Do you have a young child at school? With this website, you can enjoy reading colourful Welsh stories with them.
Welsh toys, activities and posters.
If you are teaching Welsh to others, or just learning Welsh, take a look at this.
What is a 'corpus' or 'corpora'? Large collections of different types of Welsh. Here's a list of some key ones.
Bangor University's Welsh Lexicon
A huge list of Welsh words and sentences.
Bangor University's Welsh stopwords list
A list of less important words for AI when analyzing text and processing questions.
University of South Wales's stopwords list
A list of less important words for AI when analyzing text and processing questions.
Nothing to do with lemmings or llamas. The linguists will be delighted to get to the bottom of each and every word.
Reveals the root of Welsh words, e.g. 'datblygodd' to 'datblyg-'.
Only the most passionate geeks will want this long list of words and their equivalent mathematical vectors.
A model for recognizing English named entities
Feed this tool a load of text and it will highlight the names of places, people, months, jobs... This one detects English names; there's another one available to find the Welsh ones.
Welsh punctuation and capitalization model
Where on earth did all the full stops and capital letters go? I have no idea. Well this is just the thing to put them right back in a flash.
There are models of planes, tanks and aircraft carriers. Well here is a Welsh language model especially for the Python scripting language.
Q: I'm a developer. Is this the right parser for me? A: It depends.
Grammar isn't everyone's cup of tea. But here's an automatic way to label Nouns, Verbs, Infinitives, etc. hassle-free.
The "little red car" is one thing that is described by three words. This chunker can easily combine them into one concept.
Collection of Welsh language manuscripts transcribed by OpenAI
Early examples of AI technologies transcribing Welsh handwriting.
BydTermCymru Translation Memories
This collection is of translation memory files containing published bilingual versions of documents and other materials by the Welsh Government.
If you are a developer working on text-to-speech, here's something to make sure the Welsh language equivalent of "half past seven" is uttered when the text shows "07:30". There are more rules like this available within the pack.
For developers who want to automatically score users' feedback to see if they had a positive or negative experience.
We've cast a wide net in the field of language technology and this is WordNet, which groups and cross-links Welsh words with similar meanings.
Open source Welsh spell checker lexicon so you can check your spelling.
Do you want to get to know OSCAR better? Use the Find tool, search for the word 'Welsh' and download the resources.
CLDR (Common Locale Data Repository)
Building blocks for software - the world's largest repository of locale data, including Welsh.
Looking for a language model to train speech recognition systems? Here's one that gives each word a special number or 'vector' according to how close it is to neighbouring words.
Reveals words or sets of words that could be the name of a person, place, job, etc. Named entity recognition is a key tool in natural language processing.
Welsh is one of 51 languages in this massive AI training corpus from Amazon.
An open source project to make voice recognition technology available in several languages - Welsh is of course Helo Blod's interest. Want to contribute? Record yourself reading short sentences in Welsh, or you can also validate other people's recordings.
Bangor University's Paldaruo Speech Corpus
Are you interested in developing Welsh speech technology? This corpus of audio file recordings will be a great starting point.
Macsen - Welsh language voice assistant
Macsen is a Welsh speaking AI personal assistant developed by Bangor University
It can be difficult to know how to pronounce a few words from time to time, so what hope does a synthetic voice have to do? By using Bangor University rules he will have perfect pronunciation in nothing.
For further help, there is also a pronunciation list of Welsh words which is for the use of apps and speech tools.
A linguistic model for passionate developers who want to produce Welsh speech resources.
A speech model for the real geeks who want to develop Welsh speech resources.
Bangor University's speech resources
Many of us use speech language technologies to communicate with our mobile phones and TVs. Give it a try with these resources from Bangor University.
Bangor University Welsh Transcriber
Looking for an app that types as you speak Welsh? This experimental transcriber works on Windows and it types what you say on the screen.
Gwyneth and Geraint synthetic Welsh voices
Originally, the Welsh Government commissioned these voices from RNIB Cymru. These text-to-speech voices enable blind and partially blind Welsh speakers and learners to read websites, exchange e-mail messages and read and write documents in Welsh. The next task is to choose if you are going to listen to Gwyneth or Geraint's voice today!
An innovative tool that can help if you are in danger of losing your ability to speak due to illness or a medical condition. Use your voice to develop your own personal synthetic voice.
MaryTTS - Welsh text-to-speech
If Gwyneth and Geraint have inspired you to create your own synthetic Welsh voice, this program will benefit you. Remember to give the voice a catchy name (like Blod) when you're done!
We've got bilingual speech recognition sorted for you. From literal acoustic models to more formal written language models. Bangor University have collected them all here.
A text to speech program.
An accessible, high-quality screen reader. You'll need to add your own Welsh voices, but that will be easy. You're an expert in the field now, having read through everything on this list!
Recording script for voice talent
A script that is useful for developers who want to create new artificial Welsh voices.
A guide on bilingual software for developers
Do you or your organization develop bilingual software? This guide will be perfect to help you make sure your digital project offers a great service in both Welsh and English.
Technology to help people use more Cymraeg
Want the latest on our work?
Technology and the Welsh language: call for information
We asked for ideas on Welsh tech; here's a summary of responses.
Helps with school work in the field of technology and the Welsh language.
Another generative AI tool that's starting to process Welsh.
Term base, style guides and all kinds of other useful resources to help with translation and creating original content in Welsh.
A predictive keyboard that learns and adapts to the way you write in Welsh and English at the same time.
A generative AI tool that's growing in its ability to process Welsh.
Can't quite remember what the Welsh word for "computer" is? Is it a masculine of feminine noun? Search through Cysgeir for the answer.
Don't worry about mistakes, let Cysill correct any language errors and help with the mutations!
Do you have a young child at school? With this website, you can enjoy reading colorful Welsh stories with them.
Exploration, analysis, learning, and referencing of the Welsh language - all in one handy website.
Use more Welsh in your everyday life with this open source e-mail, news feed, chat and calendar app.
Why not get a new voice for your screen reader? What's great about these is that they work bilingually in both Welsh and English.
The gift everyone has been waiting for - a hundred thousand and more Welsh articles, and more being published every day.
Fancy listening to a Welsh podcast but don't know where to start? There's something for everyone at Y Pod.
An easy way to subtitle videos in Welsh. You'll still need to proofread the text!
Standardised Welsh Place-names - Welsh Language Commissioner
The Welsh Language Commissioner's list of Welsh place names.
Guidance on simultaneous interpretation on Teams
Here's pdf and video guidance on how to set up and use simultaneous interpretation on Teams.
Technology to help people use more Cymraeg
Want the latest on our work?
Symbol support by Tobii Dynavox to help people communitcate in Welsh.
An accessible, high-quality screen reader. You'll need to add your own Welsh voices, but that will be easy. You're an expert in the field now, having read through everything on this list!
Technocamps runs Welsh coding workshops.
Bangor University's Welsh transcriber
Looking for an app that types as you speak Welsh? This experimental transcriber works on Windows and it types what you say on the screen.
Ever come across an unfamiliar word when reading a Welsh web page? Move the mouse over that word and Vocab will show you the translation.
Do you use Microsoft 365? The Welsh language interface is available free of charge.
An open source project to make voice recognition technology available in several languages - Welsh is of course Helo Blod's interest. Want to contribute? Record yourself reading short sentences in Welsh, or you can also validate other people's recordings.
If you, or your children, are learning to code with the BBC Micro:bit at school, here are extremely handy resources.
Macsen - Welsh speaking personal assistant
Macsen is a Welsh speaking AI personal assistant developed by Bangor University.
Thanks to this interactive Welsh map, you'll never need to feel lost again! The placenames all appear in Welsh and you can embed the map on your own websites too.
Welsh programs and apps.
Do you want to install a Welsh interface on your computer but don't know where to start? Watch this collection of videos which are easy to follow and show you exactly how to go about it.
Gwyneth and Geraint synthetic Welsh voices
Originally, the Welsh Government commissioned these voices from RNIB Cymru. These text-to-speech voices enable blind and partially blind Welsh speakers and learners to read websites, exchange e-mail messages and read and write documents in Welsh. The next task is to choose if you are going to listen to Gwyneth or Geraint's voice today!
You can rely on the Welsh Hacio'r Iaith language hacking community to discuss developments in the Welsh language digital world.
Would you like more Welsh content on your phone? Look through this list of iOS and Android apps, which are either in Welsh or contain an element of Welsh, and it's then just a small matter of downloading the apps.
An extension to the Chrome browser that highlights Welsh words so you can understand them more easily if you're learning Welsh.
Did you know that we’re developing a whole load of Language Technology at the Welsh Government which you can all use and reuse to your heart’s content – for free! Here’s what we're up to and here’s what we’ve done so far.