wav2vec2-base
wav2vec2_asr_base_960h
Speech recognition · family wav2vec2
macOSiOS
Apple’s model card
Apple lists this model in its Core AI model registry, which means there is a supported recipe for converting it to the .aimodel format. The converted model is not hosted by Apple; you run the export yourself with the command below.
Export presets
| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| wav2vec2-base | iOS + macOS | — | — | — |
Export it
From a checkout of apple/coreai-models, with uv installed:
uv run models/wav2vec2/export.py
Links
First seen in the catalogue 2026-11-11.