Pure-MLX implementation of Voxtral Mini 4B Realtime for low-latency
speech transcription on Apple Silicon. Avoids the transformers/torch
overhead and runs at 0.18-0.32x real-time factor.
- voxtral_mlx/model.py: MLX model with spectrogram, encoder, decoder
- voxtral_mlx/loader.py: model loading with 6-bit quantized weights
- voxtral_mlx/spectrogram.py: mel spectrogram computation in MLX
- voxtral_mlx_asr.py: VoxtralASR adapter for the AudioProcessor pipeline
