NVIDIA Canary ASR model converted to MLX format for Apple Silicon.
1from canary_mlx import load_model
2
3model = load_model("qfuxa/canary-mlx")
4result = model.transcribe("audio.wav", language="en")
5print(result)
This model is a conversion of NVIDIA's Canary ASR model to Apple's MLX framework.
Based on NVIDIA NeMo Canary model. See
NVIDIA NeMo for the original implementation.
Model weights are released under CC-BY-4.0 license (same as original NVIDIA model).
