Tiny Audio - a mazesmazes Collection

mazesmazes 's Collections

Tiny Audio

updated 3 days ago

A speech-to-text system you can train yourself: model, live demo, and the models it builds on.

mazesmazes/tiny-audio

Automatic Speech Recognition • 12.6M • Updated 2 days ago • 183 • 1

Note The published model: transcripts, word timestamps, speaker labels
Running

Agents

2

Tiny Audio Demo

🎤

2

Fast English ASR with word timestamps and speaker labels

Note Live demo
ibm-granite/granite-speech-5.0-470m-turboctc

Automatic Speech Recognition • 0.5B • Updated 10 days ago • 60.2k • 77

Note Frozen speech encoder
Qwen/Qwen3.5-2B

Image-Text-to-Text • 2B • Updated Mar 2 • 3.25M • • 435

Note Decoder (frozen, with LoRA)