A Whisper-based Korean STT trainer featuring LoRA fine-tuning for high-accuracy speech recognition with minimal resources. It offers a full pipeline—from data scraping and audio preprocessing to training, evaluation, and model merging. Optimized for Korean NLP, it’s a ready-to-use toolkit for researchers and developers.

stt

termux-bitnet

Repo · 2 stars · Python

▲ 0

⚡ Production 1.58-bit (i2_s) BitNet On-Device Inference SDK & Dual Engine for Android Termux & ARM64.

androidarm64bitnetcpp17gguf

termux-llamacpp

Repo · 1 stars · Python

▲ 0

Production-grade, prebuilt GGUF LLM runtime, model manager & OpenAI-compatible server for Android Termux & ARM64.

androidarm64edge-aiggufllamacpp

termux-stt

Repo · 1 stars · Python

▲ 0

🎙️ Production-grade On-Device Speech-to-Text & 128d X-Vector Speaker Diarization for Android Termux. whisper.cpp, Vosk, Sherpa-ONNX, and 0 PyTorch Dependency.

amevaandroidarm64audio-processingnodejs

termux-train

Repo · 1 stars · Python

▲ 0

📱 Ultra-lightweight On-Device Tensor & DAG Autograd Deep Learning Framework for Android ARM64 Termux. SafeTensors zero-copy, LoRA fine-tuning, and RoPE Transformers.

amevaandroidarm64autogradbionic

termux-vision

Repo · 1 stars · Python

▲ 0

🚀 The Sovereign On-Device Computer Vision & Multimodal VLM Inference Engine for Android Termux & ARM64 (Dual-Engine Python & Node.js/TypeScript)

androidarm64cannycomputer-visionedge-ai