FluidInference/FluidAudio

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

语言：Swift · GitHub 星标：3,247 · Fork：500

话题：ane · asr · audio · automatic-speech-recognition · avfoundation · coreml · ios · macos

在 GitHub 上查看原仓库