Mindket

Kits of AI agent skills, rules and prompts

Categories and filters
Filters
Clear filters

Listings

Summarizes, answers questions about and continues book-length text with a fine-tuned 27B model that uses Gated DeltaNet layers, in English and Japanese. For pe…

New

Haas-ja-v1.0-GGUF

sakasegawa · Kit

GGUF files of a Japanese speech recognition model that run only in speech.cpp, on macOS, Windows, Linux or the CPU alone. For people who transcribe Japanese au…

New

A 33.2B-parameter English and Japanese text generation model from the LLM-jp project. Post-trained with SFT and DPO, it has a 65,536-token context, Apache 2.0…

New

RubatoCodec

third-intelligence · Kit

Compresses speech into a fixed number of variable-length events with durations, and decodes them back as it streams. A neural speech codec for people building…

New

PP-OCRv6_manga

Kellenok · Kit

Finds and reads Japanese and Chinese text on manga, webtoon and anime pages, on a CPU. A small ONNX detector and recognizer pair from Kellenok, about 11.6 MB i…

New

PaddleOCR

PaddlePaddle · Kit

Reads text out of pictures in several languages with PaddleOCR in a Gradio page, with Chinese, English and Japanese example images. For anyone who needs the wo…

New

Qwen3.8 13.5B

kusuriya-labs · Kit

An experiment that prunes Qwen3.8-27B to half its layers and retrains it, giving a 14.7B model for Japanese and English that the author says is not practical y…

New

Haas-ja-v1.0

third-intelligence · Kit

Turns Japanese speech into text with a 615.8M speech recognition model built for speed and accuracy. For developers and teams who transcribe Japanese audio on…

New

Turns Japanese speech into text with a wav2vec2 model whose name points to hiragana output. For people who want to try Japanese speech recognition in a browser.

New

Hello Algo

krahets · Kit

krahets’s free, open source book on data structures and algorithms, with animated illustrations and code you can run with one click. It has English, Chinese, J…

New132k