projecte-aina

oTranscribe-plus

A free & open tool for transcribing audio interviews with offline ASR support

lm-catalan

Official source for Catalan Language Models and resources made within Aina project.

spacy

Pre-production releases for Spacy in Catalan

tts-api

RESTful API for synthesizing speech in catalan

datapipe

An audio ETL pipeline for generating datasets from youtube sources

espeak-ng

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

club

Official repository of the Catalan Language Understanding Benchmark (CLUB) to evaluate NLP models.

oTranscribe-plus-desktop

A free & open desktop tool for transcribing audio interviews with offline ASR support

minibot

Minibot is a demonstration of how conversational experiences can be created in Catalan using open-source language technologies.

Plume

Code for the paper "Investigating the translation capabilities of Large Language Models trained on parallel data only"

demo-mt-aina

tei2txt

Files to process pdf into txt, using grobid

catalan-language-understanding-benchmark

CLUB Site

dynamic-stance-analysis

festcat-process

scripts to process festcat dataset

pytube

A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.

amazon-sagemaker-examples

Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.

catalan_common_voice_filter

common-voice

Common Voice is part of Mozilla's initiative to help teach machines how real people speak.

common-voice-monitor

docg-pipeline

eadop-rag

flor_language_adaptation

mt-api

API for serving machine translation models.

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

rag_notebook

Rag with Flor6.3b

Recorderjs

A plugin for recording/exporting the output of Web Audio API nodes

sparknlp_ca

Repositori de recursos sparknlp pel català

text2lang

Language detection api based on ivanlau/language-detection-fine-tuned-on-xlm-roberta-base