whisper-tiny.en

This repository hosts the whisper-tiny.en models exported for the React Native ExecuTorch library as ExecuTorch .pte programs, ready to run on device.

Upstream model: whisper-tiny.en

Variants

XNNPACK int8

xnnpack/whisper_tiny_en_xnnpack_int8.pte is 8da8w (int8 dynamic activations, int8 per-channel weights). Greedy WER on LibriSpeech test-clean (150 clips): fp32 4.64, int8 4.67.

Repository structure

config.json                               37 B
coreml/config.json                        1.5 kB
coreml/whisper_tiny_en_coreml_fp16.pte    72.9 MB
mlx/config.json                           2.6 kB
mlx/whisper_tiny_en_mlx_bf16.pte          72.6 MB
mlx/whisper_tiny_en_mlx_int8.pte          57.1 MB
tokenizer.json                            2.3 MB
vulkan/config.json                        2.6 kB
vulkan/whisper_tiny_en_vulkan_fp16.pte    204 MB
vulkan/whisper_tiny_en_vulkan_int8.pte    124 MB
xnnpack/config.json                       2.6 kB
xnnpack/whisper_tiny_en_xnnpack_fp32.pte  222 MB
xnnpack/whisper_tiny_en_xnnpack_int8.pte  175 MB

Compatibility

These files are published for the ExecuTorch v1.4.1 runtime. ExecuTorch gives no forward compatibility guarantee, so an older runtime may fail to load them.

To use them in React Native ExecuTorch, pass the model constant shipped in the library's model registry to the corresponding task pipeline. See the documentation.

To load these files in your own ExecuTorch runtime, read the compatibility note first.