If you’re looking for an alternative to the Whisper stack, one option worth considering is Moshi. I’ve originally found it mentioned on X: Summary: Key Features: Mimi Codec: Training and Evaluation:
WIP: Quarkus
I started to learn something different from Spring Boot, which I use daily in my work. My choice is Quarkus – here I will gather some useful things. Long time I was…
Offline Whisper Audio Transcription and Ollama-Voice Assistant
The WhisperLive project is a real-time transcription application that utilizes the OpenAI Whisper model to convert speech input into text output. This technology can be employed for transcribing both live audio input…
PAR LLAMA: A Terminal User Interface for Easy Ollama Model Management
PAR LLAMA is a Terminal User Interface (TUI) application designed for easy management and use of Ollama based Large Language Models (LLMs). This means that users can interact with the Ollama model…
OpenAI’s New Model: A Step Forward in AI Reasoning
The latest development from OpenAI has brought forth a new model, aptly named o1. According to the company, this model has been designed to take its time thinking before responding, thus enabling…
ColPali and Byaldi for reading PDFs with images, Reflection-70B
Multi-modal documents were always a problem, but what I can read now AI developers already made a huge progress, beating traditional PDF parsers. Now we have at least 3 solutions available as…
AI programming tools
Claude, Cursor or Replit agents? It seems like the market of application creation AI tools is growing fast. After a very good Claude Sonnet application creation chat, developers moved to Cursor and…
WIP: Hugging Face cheatsheet part 1
As prerequisite we need to have Python, pip, venv installed, for Git there is a need for lfs, because Hugging Face supports files larger than 5GB in repos. To work with with…
ComfyUI v0.2.0 released
Major updates in v0.2.0:
Flux controlnet support for Xlab, InstantX controlnets
improvements to the queue UI. You can view all outputs generated by the same task now
Bookmarking in the node library + recursive expanding / collapsing node library folders
First US laws to ban AI art and gen sites
This was inevitable, but I’m not sure if it’s good the way they want to introduce it. On one hand, IP for human artists will be better protected, and users will be…