Downloads · 30 days
1.8K
23% of all-time downloads
react-native-executorch-whisper-base.en
software-mansion/react-native-executorch-whisper-base.en
react-native-executorch-whisper-base.en is a automatic speech recognition model from software-mansion. Use it when you need speech turned into text. It is set up for executorch. The card lists the license as apache-2.0.
This repository hosts the whisper-base.en models exported for the React Native ExecuTorch library as ExecuTorch .pte programs, ready to run on device.
All-time downloads
7.9K
Public
Repo size
4.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pte1.6 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- executorch
- License
- apache-2.0
- Access
- Public
- Created
- Aug 20, 2025
- Updated
- Sep 9, 2026
- SHA
- ce992bbc
Model card
From the Hugging Face model README
whisper-base.en
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
| Path | Backend | Precision |
|---|---|---|
coreml/whisper_base_en_coreml_fp16.pte | coreml | fp16 |
mlx/whisper_base_en_mlx_bf16.pte | mlx | bf16 |
mlx/whisper_base_en_mlx_int8.pte | mlx | int8 |
vulkan/whisper_base_en_vulkan_fp16.pte | vulkan | fp16 |
vulkan/whisper_base_en_vulkan_int8.pte | vulkan | int8 |
xnnpack/whisper_base_en_xnnpack_int8.pte | xnnpack | int8 |
xnnpack/whisper_base_en_xnnpack_fp32.pte | xnnpack | fp32 |
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.
- Task
- Automatic Speech Recognition
- Library
- executorch
- License
- apache-2.0
- Languages
- en
- Created
- Aug 20, 2025
- Updated
- Sep 9, 2026