mirror of
https://github.com/QuentinFuxa/WhisperLiveKit.git
synced 2026-03-07 14:23:18 +00:00
a4da246ea5
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