software-mansion
/

react-native-executorch-whisper-tiny

Automatic Speech Recognition

Model card Files Files and versions

react-native-executorch-whisper-tiny / mlx

136 MB

Ctrl+K

Ctrl+K

7 contributors

History: 6 commits

aceOfDiamonds's picture

Stop restating quantized, and drop the unused default

9a78f41 11 days ago

config.json

2.69 kB
Stop restating quantized, and drop the unused default 11 days ago
whisper_tiny_mlx_bf16.pte

76.1 MB
xet

Update .pte files for v0.10.0 about 1 month ago
whisper_tiny_mlx_int8.pte

59.9 MB
xet

Add int8 MLX variant alongside bf16 25 days ago