BS Software Engineering at Virtual University | The Strategic Choice
By: Sohaib Malik, Software Engineer & Certified AI EngineerContinue reading on Medium »
Artificial Intelligence, computer science, pakistan, software-engineering, uv
uv
datasette-lite, microsoft, mlx, prince-canuma, python, speech-to-text, uv
microsoft/VibeVoice
microsoft/VibeVoice
VibeVoice is Microsoft’s Whisper-style audio model for speech-to-text, MIT licensed and with speaker diarization built into the model.
Microsoft released it on January 21st, 2026 but I hadn’t tried it until today. Here’s a one…
Artificial Intelligence, data-science, pip, python, uv
I Stopped Using pip for New Python Projects uv Changed Everything
If you write Python long enough, you eventually accept a weird ritual as normal.Continue reading on Towards AI »
ai, gemma, generative-ai, LLMs, mlx, python, speech-to-text, uv
Gemma 4 audio with MLX
Thanks to a tip from Rahim Nathwani, here’s a uv run recipe for transcribing an audio file on macOS using the 10.28 GB Gemma 4 E2B model with MLX and mlx-vlm:
uv run –python 3.13 –with mlx_vlm –with torchvision –with gradio \
mlx_vlm.generat…
ai, ai-assisted-programming, ai-ethics, andrej-karpathy, claude-code, generative-ai, hugging-face, llm, LLMs, local-llms, Training Data, uv
Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer
Trip Venturella released Mr. Chatterbox, a language model trained entirely on out-of-copyright text from the British Library. Here’s how he describes it in the model card:
Mr. Chatterbox is a language model trained entirely from scratch on a corp…