Speech AI models for Apple Silicon via MLX. ASR, TTS, VAD, diarization, speaker embedding.
-
aufklarer/Qwen3-ASR-0.6B-MLX-4bit
0.3B • Updated • 149k • 3 -
aufklarer/WeSpeaker-ResNet34-LM-MLX
Audio Classification • 6.63M • Updated • 61.4k • 2 -
aufklarer/PersonaPlex-7B-MLX-4bit
Audio-to-Audio • Updated • 109k • 35 -
aufklarer/Qwen3-ForcedAligner-0.6B-4bit
Audio Classification • 0.4B • Updated • 36.5k • 1