---
license: apache-2.0
tags:
  - executorch
  - metal
  - apple-silicon
  - speech-to-text
  - on-device
pipeline_tag: automatic-speech-recognition
base_model: openai/whisper-tiny
---

# Whisper-Tiny-ExecuTorch-Metal

Pre-exported [ExecuTorch](https://github.com/pytorch/executorch) `.pte` files
for [Whisper Tiny](https://huggingface.co/openai/whisper-tiny) with **Metal**
backend (Apple GPU). Speech-to-text with GPU acceleration on macOS Apple Silicon.

For the XNNPACK (CPU) variant, see
[Whisper-Tiny-ExecuTorch-XNNPACK](https://huggingface.co/younghan-meta/Whisper-Tiny-ExecuTorch-XNNPACK).

## Installation

```bash
git clone https://github.com/pytorch/executorch/ ~/executorch
cd ~/executorch && EXECUTORCH_BUILD_KERNELS_TORCHAO=1 TORCHAO_BUILD_EXPERIMENTAL_MPS=1 ./install_executorch.sh
make whisper-metal
```

## Download

```bash
pip install huggingface_hub
huggingface-cli download younghan-meta/Whisper-Tiny-ExecuTorch-Metal --local-dir ~/whisper_tiny_metal
```

## Run

```bash
DYLD_LIBRARY_PATH=/usr/lib:$(brew --prefix libomp)/lib \
  cmake-out/examples/models/whisper/whisper_runner \
    --model_path ~/whisper_tiny_metal/model.pte \
    --tokenizer_path ~/whisper_tiny_metal/ \
    --processor_path ~/whisper_tiny_metal/whisper_preprocessor.pte \
    --audio_path ~/whisper_tiny_metal/poem.wav \
    --temperature 0
```

## Export Commands

```bash
pip install optimum-executorch

# Model (fp32 -- bfloat16 has a Metal shader compilation issue)
optimum-cli export executorch \
    --model openai/whisper-tiny \
    --task automatic-speech-recognition \
    --recipe metal \
    --output_dir ./whisper_tiny_metal

# Preprocessor
python -m executorch.extension.audio.mel_spectrogram \
    --feature_size 80 --stack_output --max_audio_len 300 \
    --output_file ./whisper_tiny_metal/whisper_preprocessor.pte
```

## More Info

- [Official ExecuTorch Whisper guide](https://github.com/pytorch/executorch/tree/main/examples/models/whisper)
- [Original model](https://huggingface.co/openai/whisper-tiny)