software-mansion/react-native-executorch-whisper-base

whisper-base

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

Upstream model: whisper-base

Variants

Path	Backend	Precision
coreml/whisper_base_coreml_fp16.pte	coreml	fp16
mlx/whisper_base_mlx_bf16.pte	mlx	bf16
mlx/whisper_base_mlx_int8.pte	mlx	int8
vulkan/whisper_base_vulkan_fp16.pte	vulkan	fp16
vulkan/whisper_base_vulkan_int8.pte	vulkan	int8
xnnpack/whisper_base_xnnpack_fp32.pte	xnnpack	fp32
xnnpack/whisper_base_xnnpack_int8.pte	xnnpack	int8

XNNPACK int8

xnnpack/whisper_base_xnnpack_int8.pte is 8da8w (int8 dynamic activations, int8 per-channel weights). Greedy WER (CER for zh) against the fp32 file, LibriSpeech test-clean (150 clips) and FLEURS (80 per language):

	en	de	es	pl	fr	zh
fp32	4.12	24.88	13.66	47.35	40.76	21.27
int8	3.94	25.04	13.87	46.39	41.09	21.27

Repository structure

config.json                            34 B
coreml/config.json                     1.5 kB
coreml/whisper_base_coreml_fp16.pte    140 MB
mlx/config.json                        2.6 kB
mlx/whisper_base_mlx_bf16.pte          139 MB
mlx/whisper_base_mlx_int8.pte          97.8 MB
tokenizer.json                         2.4 MB
vulkan/config.json                     2.6 kB
vulkan/whisper_base_vulkan_fp16.pte    335 MB
vulkan/whisper_base_vulkan_int8.pte    196 MB
xnnpack/config.json                    2.6 kB
xnnpack/whisper_base_xnnpack_fp32.pte  380 MB
xnnpack/whisper_base_xnnpack_int8.pte  254 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.