Automatic Speech Recognition
Transformers
Safetensors
MLX
Min Nan Chinese
Chinese
whisper
taiwanese-hokkien
taigi
low-resource-language
fine-tuned
stt
Instructions to use rickylin20260522/Breeze-ASR-26-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rickylin20260522/Breeze-ASR-26-mlx with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="rickylin20260522/Breeze-ASR-26-mlx")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("rickylin20260522/Breeze-ASR-26-mlx") model = AutoModelForSpeechSeq2Seq.from_pretrained("rickylin20260522/Breeze-ASR-26-mlx", device_map="auto") - MLX
How to use rickylin20260522/Breeze-ASR-26-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Breeze-ASR-26-mlx rickylin20260522/Breeze-ASR-26-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
- Downloads last month
- 11
Model size
2B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for rickylin20260522/Breeze-ASR-26-mlx
Base model
openai/whisper-large-v2 Finetuned
MediaTek-Research/Breeze-ASR-26