Macsen 4+

Scroll down for English

Mae Macsen yn feddalwedd cynorthwyydd personol Cymraeg cod agored tebyg i Alexa neu’r Google Assistant. Ystyr cod agored yw y gall unrhyw un weld, addasu a dosbarthu’r cod fel yr hoffen nhw. Mae’n gweithio fel ap ar ffôn neu dabled yn ogystal â fersiwn ar-lein. Mae’n bosib siarad gyda Macsen mewn Cymraeg naturiol er mwyn gofyn iddo gwblhau tasgau neu ofyn am wybodaeth,

Erbyn hyn, mae gan ap Macsen nifer o sgiliau, gan gynnwys y gallu i chwarae cerddoriaeth Cymraeg ar Spotify, rhaglenni ar S4C Clic, rhoi’r golau ymlaen neu i ffwrdd, adrodd y newyddion diweddaraf, darparu rhagolygon y tywydd, defnyddio ChatGPT, cyfieithu lleferydd Saesneg i destun Cymraeg a thrawsgrifio lleferydd Cymraeg i destun. Felly mae modd teipio yn ogystal â defnyddio’r llais i ofyn cwestiynau a rhoi gorchmynion i Macsen.

Rydyn ni’n defnyddio’r project hwn i ddangos beth allwn ni greu wrth ddatblygu technoleg lleferydd a deallusrwydd artiffisial Cymraeg. Rydyn ni’n cyhoeddi’r cydrannau a’r adnoddau perthnasol yma yn agored ar y Porth Technolegau Iaith, er mwyn i ddatblygwyr eraill hefyd fedru’u defnyddio. Rydyn ni wrthi yn gwneud ymchwil pellach i’w wella, a’i alluogi mewn sefyllfaoedd eraill.

Macsen is an open source Welsh language voice assistant similar to Alexa or the Google Assistant. Open source means that anyone can see, adapt and distribute its code as they wish. It works as an app for phones and tablets. An online version is also available. You can speak in Welsh to Macsen to ask it to do various tasks or provide information.

Its growing set of skills include the ability to play Welsh Language music through Spotify, programmes through S4C Clic, turn the light on or off, get the news and weather, use ChatGPT, translate spoken English to Welsh text and transcribe Welsh speech to text.

We are using this project to show what we can create when developing Welsh language speech technology and artificial intelligence. We publish relevant components and resources with open licences on the Welsh National Language Technology Portal, so that other developers can also use them. We are also undertaking further research to improve it, and to enable it in other environments.