AI product Open source
hayamimi is a local, real-time multilingual speech-to-text tool that produces live subtitles, a browser dashboard, speaker labels, and optional translation without a GPU or cloud API. It detects the language of each utterance and routes it to a dedicated specialist model for Japanese, Chinese, Korean, Cantonese, English, and European languages, with a broad Omnilingual ASR fallback for other languages.
The models run as quantized INT8 ONNX models through sherpa-onnx, without PyTorch or CUDA. The pipeline updates partial subtitles while speech is in progress, emits finalized lines shortly after speech stops, and can perform a second batch-decoding pass after silence to produce a refined transcript. Speaker labeling uses CAM++ embeddings and is intended for turn-taking rather than full diarization.
The `--serve` option starts a local HTTP server with a live dashboard and an OBS browser-source overlay. Audio can also be supplied over WebSocket, and model eviction keeps resident models below a configurable memory cap, with the default under 2 GB of RAM. The project reports 5.8% character error rate on its Japanese broadcast-audio scorecard and 10–50× real-time processing on a six-core desktop CPU.
2 uses taken from transcripts — each links to the moment in the video.
A real-time speech-to-text tool that runs locally on a CPU without sending audio to the cloud. It detects the spoken language and routes each utterance to a specialist Japanese, Chinese, or English model, with a broad fallback.
An open-source CPU-only speech-to-text tool for real-time multilingual subtitles. It provides speaker labels, live translation, specialist quantized language models, and an OBS overlay without requiring a GPU or cloud service.
2 in the library.