A conversion of OpenAI's Whisper tiny English model to ONNX format, optimized for use with Transformers.js. It enables client-side speech-to-text transcription in web applications. The model is significantly smaller than full Whisper variants while maintaining reasonable accuracy for English audio.
Whisper Tiny.en is a Voice, TTS & speech project. It focuses on running automatic speech recognition models directly in web browsers or JavaScript environments without server dependency. It is built as an open-source project for developers. The project is open source (Open Source). It ships for the web, the command line, and API.
It is developed by ONNX Community, and it first shipped in 2024. Among its 3 catalogued features are Speech Recognition, ONNX Runtime, and Browser Inference. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do