High-performance, lightweight libraries optimized for local inference and edge hardware.
Install package locally:
$ pip install nanowakewordTrain custom model:
$ nanowakeword -c ./config.yamlAn automated training toolkit designed for deploying production-grade, low-latency custom wake words directly onto edge devices and microcontrollers. Nanowakeword automates audio data synthesis, synthetic background noise mixing, and neural model quantization.
GitHub Repository →Install package locally:
$ pip install phonemizeA lightweight, zero-dependency, pure-Python library designed to convert raw text inputs into phonetic IPA representations. Essential for building high-fidelity Text-to-Speech (TTS) frontends and NLP text processing chains.
A live feed of our active machine learning datasets on HuggingFace. The registry cycles automatically below.
Read the methodology, mathematical formulations, and engineering optimizations behind our open-source tools.
We describe our custom training pipeline that compresses and compiles speech wake-word models. By incorporating synthetic soundscape augmentation and post-training integer-8 quantization, we achieve robust wake word recognition under 15KB of local SRAM.
This paper presents a zero-dependency phonetic translation toolkit that converts multi-language orthographic text to the International Phonetic Alphabet (IPA). We demonstrate a 40% inference latency reduction using native dictionary mappings.
We present a dynamic sampling strategy for alignment datasets. By clustering prompt logic trees C_k and sampling inputs x_i proportional to historical losses, we achieve higher training convergence on multi-step reasoning tasks.