Index
All Articles
Everything published here, newest first.
105 articles · Page 2 of 11
23 Cheshvan 5787
My curated AI indexes on GitHub: what each list covers
Fifteen curated AI lists and awesome-lists I keep on GitHub: agents and harnesses, coding tools, evals, LLM councils, simulations, voice and Whisper. What each covers, how big it is, when it was last updated and which are snapshots.
23 Cheshvan 5787
Can image models spell the labels? A first look at my Tech Graphics Benchmark
Limited evaluation: 95 images from five cheap image models, 12 annotated so far. In this run, 10 of 11 had every label spelled exactly; the problems were composition, stretching and style. Not a verdict on any model.
23 Cheshvan 5787
Datasets for fine-tuning speech recognition on your own voice
A guide to my public Hugging Face datasets of read-aloud sentences for fine-tuning speech recognition: tech, Linux, smart home, AI agents, homophones, Hebrew code-switching and voice notes. What each holds and which to use.
23 Cheshvan 5787
Transcribe a WhatsApp chat export, voice messages included
How to read and transcribe a WhatsApp chat export: WhatsApp Export Unpacker parses the ZIP, transcribes voice messages with Whisper, and builds a text file, PDF and WhatsApp-style HTML viewer, with optional anonymisation of participants.
23 Cheshvan 5787
My AI prompt libraries, and which one to use
A guide to my open-source system prompt library and its siblings: prompts for NotebookLM, Open WebUI, Roo Code and ChatGPT, tools for writing prompts, and which of the twelve repositories and Hugging Face datasets to use for what.
23 Cheshvan 5787
Obsidian AI plugins, sorted: a categorised list of 86 LLM plugins
A categorised list of 86 Obsidian plugins that bring AI and LLMs into a vault, from local Ollama setups to chat-with-notes RAG and voice input, sorted by GitHub stars. Auto-organised from GitHub metadata, not hand-reviewed.
23 Cheshvan 5787
Contextual Sentence Creator: a 3B model that writes ASR training sentences
A Granite 4.2 3B fine-tune that writes natural sentences using a given term, for recording speech recognition training data. 95.7% of sentences pass the acceptance check; GGUF build included.
23 Cheshvan 5787
Fritter: a Parakeet fine-tune for English tech dictation
Fritter is my Parakeet TDT 0.6B v2 fine-tune for English dictation without Hebrew: tech terms, numbers and brand names. Tech WER falls from 7.53% to 4.01% on my voice. Browser demo and GGUF builds.
23 Cheshvan 5787
Hey Yossi: a custom wake word for Home Assistant
Hey Yossi is a custom wake word for Home Assistant, trained on real recordings, in two builds: openWakeWord for the server and Pi, microWakeWord for ESPHome, Voice PE and Android. 95% recall in testing.
23 Cheshvan 5787
S1-ASR-Cleanup: cleaning up dictation with a fine-tuned S1-mini
A fine-tune of S1-mini by Superwhisper that cleans speech-to-text dictation: paragraphs, dates and money as digits, contractions and fillers handled. 0.6B, with GGUF builds for llama.cpp and phones.