Open-source Oído beats Whisper-tiny on a $5 microcontroller

The Lokutor team released Oído, an open-source speech recognition model using a 13M-parameter int8 NVIDIA Conformer-CTC Small that runs on an ESP32-S3 with 8MB PSRAM, no GPU or NPU. It achieves LibriSpeech WER of 3.7/8.2 versus 6.3/15.9 for Whisper tiny.en.

• Cactus Releases Whistle: A 16.9MB Speech-to-Text Model2026-10-06
• Nvidia Nears $6 Trillion Market Cap at Record High2026-10-06
• Nvidia Faces Questions Over AI Chip Smuggling Into China2026-10-05
• User slams 64GB DGX Spark priced same as 128GB model2026-10-05
• 19-Year-Old Founder's Ghost Raises $11M Seed Round2026-10-05