techiaith/xlsr-fine-tuning-week

This repository has been archived on 01/Nov/2022
Stars
3
Rank 3,963,521 (Top 79 %)
Language
Python
Created over 3 years ago
Updated over 3 years ago

techiaith/xlsr-fine-tuning-week

techiaith

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Cod cyd fynd a wythnos mireinio XLSR Facebook gyda HuggingFace ar gyfer y Gymraeg / Code for fine tuning Facebook XLSR models with HuggingFace for Welsh

docker-moses-smt

Hwyluso cyfieithu peirianyddol MosesSMT i'r Gymraeg // Making MosesSMT machine translation easier for Welsh (and other languages)

docker-huggingface-stt-cy

Adnabod lleferydd Cymraeg i'r Gymraeg gyda HuggingFace // Speech Recognition for Welsh with HuggingFace

pyfestival

Amlapiwr Python C ar gyfer hwyluso rhaglennu gyda Festival | A Python C wrapper for simple coding with Festival

docker-deepspeech-cy

Hyfforddi modelau adnabod lleferydd Cymraeg gyda Mozilla DeepSpeech // Train Welsh language speech recognition models with Mozilla DeepSpeech.

docker-marytts

Lleisiau synthetig cadwynedig Cymraeg gyda MaryTTS a Docker // Welsh concatenative TTS voices with MaryTTS and Docker

lecsicon-cymraeg-bangor

Lecsicon cynhwysfawr o eirffurfiau'r Gymraeg yn seiliedig ar ddata gwirydd sillafu a gramadeg Cysill | A comprehensive lexicon of Welsh-language wordforms based on data from the Cysill spelling and grammar checker

macsen-flutter

Ap cynorthwyydd llais iaith Gymraeg i Android ac iOS // Welsh language voice assistant app for Android and iOS

hunspell-cy

Fersiwn wedi'i ddiweddaru o'r fersiwn Cymraeg o wirydd sillafu Hunspell. | An updated version of the Welsh version of the Hunspell spellchecker.

geiriadur-ynganu-bangor

Geiriadur Ynganu Prifysgol Bangor // Bangor University Pronunciation Dictionary

macsen-sgwrsfot

Cydran adnabod bwriad a sgwrsfot yr ap Macsen // Intent parser and chatbot component for the Macsen app

model-tagiwr-spacy-cy

Model spaCy (2.3.2) sy'n cynnwys tagiwr rhan ymadrodd Cymraeg cychwynnol sydd â chywirdeb o 91% | A Welsh-language spaCy (2.3.2) model featuring a pos tagger that achieves 91% accuracy on unseen data.

geiriau-mwyaf-aml

Rhestrau geiriau mwyaf aml y Gymraeg a Saesneg // Wordlists of the most common wordforms in Welsh, and the most common English words used in Welsh.

llais_festival

Data llais Cymraeg ddeuffon er mwyn llwytho i lawr a’u rhedeg o fewn gosodiad lleol o Festival (ar Linux, Raspberry Pi neu Windows) | Welsh diphone voice data for loading into your local installation of Festival (on Linux, Raspberry Pi or Windows)

welsh-lts

Rheolau ynganu Cymraeg | Welsh letter-to-sound rules

lecsicon-cymraeg-bangor-enghreifftiau

Enghreifftiau o ddefnyddio Lecsicon Cymraeg Bangor // Examples of code utilising the Bangor University Welsh language lexicon.

brawddegau-tagiedig

Corpws o frawddegau CC0 mewn fformat jsonl, gyda rhannau ymadrodd y tocynnau (geiriau etc.) wedi'u tagio â thagiau Universal Dependencies. | A Corpus of CC0 sentences in the jsonl format, tagged with Universal Dependency part-of-speech tags.

spacy-lang-cy

Ffolder lang 'cy' ar gyfer ychwanegu'r Gymraeg i spaCy 2.3.2 | A 'cy' lang folder that adds Welsh to spaCy 2.3.2

trawsgrifiwr-arlein

Cod gwefan Trawsgrifiwr Ar-lein gan Uned Technolegau Iaith, Prifysgol Bangor // // The code for the Trawsgrifiwr Ar-lein website by the Language Technologies Unit, Bangor University

julius-cy

Ffeiliau ar gyfer adnabod lleferydd Cymraeg drwy Julius | Files for realising Welsh speech recognition with Julius

trawsgrifiwr-windows

Ap Windows sy'n trawsgrifio lleferydd Cymraeg i destun / A Windows app that transcribes Welsh language speech to text.

offer-trin-iaith

Offer ar gyfer hwyluso trin agweddau o destunau Cymraeg, er enghraifft treigladau ac ati | Tools for facilitating the manipulation of Welsh texts, including mutation.

docker-coqui-tts-cy

Lleisiau synthetig testun i leferydd dwyieithog Cymraeg a Saesneg // // Bilingual Welsh and English synthetic text to speech voices

docker-marian-nmt

Meddalwedd ac offer docker i weithio gyda Marian NMT | Software and tools for working with Marian NMT

docker-festival-tts-cy-api

kaldi-cy

Adnabod lleferydd Cymraeg gyda Kaldi ASR | Welsh language speech recognition using Kaldi ASR

parsiwr-dibyniaethau

Parsiwr dibyniaethau Cymraeg ar gyfer spaCy. | A Welsh language dependency parser for spaCy.

spacy_cy_tag_lem_ner_lg

Model tagio POS, NER a fectorau Cymraeg spaCy 3.5 | A Welsh POS tagging, NER and vector model for spaCy 3.5

ataleiriau

Rhestr o ataleiriau Cymraeg | Welsh Stopwords List

piper-cy

Lleisiau all-lein Cymraeg || Welsh offline voices

corpws-CC0

Corpws o frawddegau o destun Cymraeg wedi'u trwyddedu o dan drwydded CC0 | A corpus of Welsh texts licensed under the CC0 licence

hunspell-cy-llafar

Fersiwn Cymraeg llafar o wirydd sillafu Hunspell. | Spoken Welsh version of the Hunspell spellchecker.

enwau_ffug

Ffeiliau i'w hychwanegu at lyfrgell Faker er mwyn creu enwau personol ac enwau lleoedd Cymraeg a Chymreig ffug / Additional files for the Faker library to enable the creation of fake Welsh-language and geographicaly Welsh personal names and place-names

seilwaith

Offer hwyluso creu Adnabod Lleferydd Cymraeg gyda HTK, IRSTLM, Julius a Docker | Welsh Speech Recognition with HTK, IRSTLM, Julius and Docker

cymreigio-porwyr

A website plugin for notifying visitors that that their browser’s content language preferences are still set to English (US) and assist changing to Welsh (cy) | Ategyn wefannau sy'n tynnu at y ffaith mai Saesneg (UDA) yw dewis iaith cynnwys ddiofyn porwyr a'u helpu i'w newid i Cymraeg (cy)

docker-metashare

A Dockerfile and associated files for simple installation of a META-SHARE node

Festival_Windows

Project Visual Studio ar gyfer adeiladu Festival ar gyfer Windows a'i defnyddio drwy COM | A Visual Studio project for building Festival for Windows and interacting through COM

word2vec-cy

Model Iaith Fectorau Word2vec ar sail corpora ymchwil yr Uned Technolegau Iaith a gasglwyd o ffynonellau amrywiol at ddibenion ymchwil fel cynhyrchu modelau iaith. | A Word2vec Language Model based on the Language Technologies Unit's research corpora.

brawddegau-adnabod-lleferydd

Corpws brawddegau CC0 ar gyfer promptiau adnabod lleferydd Cymraeg // A corpus of CC0 licensed sentences as prompts for Welsh speech recognition training

hacio-deepspeech-cymraeg

I gyd-fynd a'r Hacio'r Iaith bach 2020, dyma amgylchedd ac enghreifftiau syml o ddefnyddio modelau DeepSpeech Cymraeg techiaith ar gyfer trawsgrifio fideos YouTube.