Transcribe Audio and Generate Subtitles with OpenAI Whisper: A Practical Tutorial
Transcribe audio with OpenAI Whisper, generate readable SRT subtitles with word timestamps, burn them into video, and speed everything up with faster-whisper.
AI Tutorials
Read Full News
Generate Images Locally with Stable Diffusion and ComfyUI: A Beginner’s Workflow Guide
Install ComfyUI, load a Stable Diffusion checkpoint, and generate your first image with the default text-to-image workflow — then learn what each node does.
Fine-Tune a Small Open Model with LoRA Using Unsloth: A Hands-On Walkthrough
Fine-tune a small open model with LoRA and Unsloth on a free GPU: 4-bit loading, adapter training with TRL, saving the adapter, and running inference.
Build a RAG Pipeline with Open-Source Tools: Embeddings, Qdrant and a Local LLM
Build a complete RAG pipeline from open-source parts: chunk documents, embed them, store vectors in Qdrant, and answer with a local LLM.
How to Run an Open-Weights LLM Locally with Ollama: A Practical Guide
Install Ollama, pull an open-weights model, customize it with a Modelfile, and call it from your own code via its local REST API — step by step.
LLM Quantization Explained Hands-On: GGUF with llama.cpp and AWQ with llm-compressor
Quantize LLMs hands-on: convert models to GGUF and quantize with llama.cpp, then produce AWQ checkpoints with llm-compressor for fast GPU serving.
Automate Document Processing with Local AI: Parse Invoices with Docling and Ollama
Automate invoice processing locally: parse PDFs with Docling, extract structured fields with Ollama into JSON, and write clean rows to CSV — no cloud APIs.
Evaluate an Open LLM with the EleutherAI Eval Harness: A Hands-On Guide
Evaluate open LLMs with the EleutherAI lm-evaluation-harness: run standard benchmarks, compare models fairly, and read the results like a practitioner.
Serve an Open Model at Speed with vLLM: Setup, Configuration and Benchmarking
Serve an open model with vLLM behind an OpenAI-compatible API: installation, the configuration flags that matter, and honest benchmarking with vllm bench.
Build a Simple AI Agent with Hugging Face smolagents: Tools, Code and Local Models
Build a working AI agent with Hugging Face smolagents: give a CodeAgent web search and custom Python tools, then run it locally or via the HF API.