Model reference · open weights

react-native-executorch-whisper.en

Not for GPU servers Audio software-mansion Speech→text 1 build Open weights 2k dl/mo

react-native-executorch-whisper.en is an open-weight audio or speech model from software-mansion. Built for phones (ExecuTorch). It does not run on a GPU server.

  • react-native-executorch-whisper.en is an automatic speech recognition model for English, published by software-mansion.
  • It consists of whisper-base.en variants exported as ExecuTorch .pte programs for on-device execution in React Native.
  • The repository provides files for coreml, mlx, vulkan, and xnnpack backends with fp16, bf16, int8, and fp32 precision, and is licensed under apache-2.0.

Summary of the software-mansion/react-native-executorch-whisper-base.en model card, 2026-10-01

What it is

Released bysoftware-mansion
Released2025-08-20

From the model card

What software-mansion says about react-native-executorch-whisper.en

Read the model card

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

Upstream model: whisper-base.en

Variants

PathBackendPrecision
coreml/whisper_base_en_coreml_fp16.ptecoremlfp16
mlx/whisper_base_en_mlx_bf16.ptemlxbf16
mlx/whisper_base_en_mlx_int8.ptemlxint8
vulkan/whisper_base_en_vulkan_fp16.ptevulkanfp16
vulkan/whisper_base_en_vulkan_int8.ptevulkanint8
xnnpack/whisper_base_en_xnnpack_int8.ptexnnpackint8
xnnpack/whisper_base_en_xnnpack_fp32.ptexnnpackfp32

Repository structure

config.json                               37 B
coreml/config.json                        1.5 kB
coreml/whisper_base_en_coreml_fp16.pte    140 MB
mlx/config.json                           2.6 kB
mlx/whisper_base_en_mlx_bf16.pte          139 MB
mlx/whisper_base_en_mlx_int8.pte          97.8 MB
tokenizer.json                            2.3 MB
vulkan/config.json                        2.6 kB
vulkan/whisper_base_en_vulkan_fp16.pte    335 MB
vulkan/whisper_base_en_vulkan_int8.pte    196 MB
xnnpack/config.json                       2.6 kB
xnnpack/whisper_base_en_xnnpack_fp32.pte  380 MB
xnnpack/whisper_base_en_xnnpack_int8.pte  236 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.

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Running it

Where it runs

Built for phones (ExecuTorch). It does not run on a GPU server.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms