This model is based on
MediaTek-Research_Breeze-ASR-25, a state-of-the-art automatic speech recognition (ASR) model.
It has been converted into the CoreML format for compatibility with Whisperkit, enabling efficient ASR inference on Apple Silicon devices.
Breeze-ASR-25 is a high-performance automatic speech recognition model developed by MediaTek Research. This CoreML version enables on-device inference on Apple Silicon devices through Whisperkit integration.
1import whisperkit
2
3# Load the model
4model = whisperkit.load_model("your-username/Breeze-ASR-25_coreml")
5
6# Transcribe audio
7result = model.transcribe("path/to/audio.wav")
8print(result.text)
This model is licensed under the Apache 2.0 License.
1@article{breeze-asr-25,
2 title={Breeze-ASR-25: Efficient Speech Recognition for Mobile Devices},
3 author={MediaTek Research},
4 journal={arXiv preprint},
5 year={2024}
6}
