Software🎙️
speech-swift (Kyutai STT)
A Swift/MLX runtime for Kyutai's streaming speech recognition on Apple Silicon. The reference checkpoint is the STT-1B (English and French) in INT8/FP16, with a causal Mimi encoder (32 audio codes every 80ms). Supports INT4/INT8 exports. CC-BY-4.0 weights license.
VoceSTTApple SiliconMLX

