hermes-ai.netis an unofficial, independent community guide to Hermes Agent, with localized docs, release notes, desktop notes, and practical setup paths.

modelAudio Open Source

Xenova's Whisper Tiny Brings Free Speech Recognition to Any Browser

A 78 MB ONNX port of OpenAI's Whisper Tiny English model is quietly powering hundreds of browser-based transcription apps, no server required.

Source

AlphaSignal

Published

Sep 30, 2026, 10:01 AM

Author

AlphaSignal Newsroom

Read

1 min read

A 78 MB ONNX port of OpenAI's Whisper Tiny English model is quietly powering hundreds of browser-based transcription apps, no server required.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

AlphaSignal · model

YuE2 Now Generates Full Songs Locally Without Python or PyTorch

NVIDIA AI · model

NVIDIA's BigVGAN v2 Hits 44.1 kHz Audio With 3x Faster CUDA Inference

AlphaSignal · repo

Next reads

YuE2 Now Generates Full Songs Locally Without Python or PyTorch

NVIDIA's BigVGAN v2 Hits 44.1 kHz Audio With 3x Faster CUDA Inference

Norwegian Developer Builds a Raspberry Pi Frame That Draws Birds it Hears