In recent years, text-to-speech (TTS) models have advanced enormously. Month after month, new releases improved pronunciation, prosody, and overall audio quality. Unfortunately, most of those models were designed for English, or at best compatible with only a few languages. The tools available for generating Basque voices used to be quite limited: paid proprietary systems (such as Elhuyar’s neural TTS, developed by Orai), or older robotic voices that had clearly fallen behind. ...

Over the last few days, I have been fine-tuning Nvidia Parakeet for Basque, and I have published the result here. The goal was simple: to have a lightweight Basque speech-to-text model that runs fast and is practical on modest hardware. Accuracy vs speed To be clear, this model is not as accurate as my best Basque Whisper model: xezpeleta/whisper-large-v3-eu However, it has a major advantage: it is very fast and can run on CPU-only setups. ...

Lynis is an open-source security auditing tool for Linux systems. It scans file permissions, kernel parameters, installed packages, running services, and more. It’s read-only — it never changes anything on the system, just reports what it finds. The problem comes when managing multiple servers. Running Lynis on each one, collecting the reports, and tracking changes over time becomes tedious quickly. A centralized dashboard for Lynis I built TrikuSec to solve this. It’s a centralized platform that collects Lynis audit reports from multiple servers and presents them in a single web dashboard. ...

This guide explains the steps to convert models published on HuggingFace to GGUF format. The GGUF format offers the possibility to run models efficiently on our computers. For this, we can use tools like Llama.cpp or Ollama. Download Llama.cpp To convert to GGUF format locally on our machine, we first need to download llama.cpp to be able to use its conversion tools. # Clone the llama.cpp repository git clone https://github.com/ggml-org/llama.cpp.git Prepare the environment We will use uv to prepare the environment and install necessary dependencies. If you haven’t installed it, you will need to install it. ...

Recently, the HiTZ center published the Latxa VL models. These models are based on Qwen3-VL models and possess vision capabilities. Currently, two sizes are available, both very small: models with 2B and 4B parameters. The tests presented below were performed with the 4B model. Models that know Basque Generally, models of such small size tend to only have the ability to answer decently in English. These Latxa VL models, however, have been trained to perform in Basque. ...