I did a MLX "streaming ASR + LLM + streaming TTS" pipeline in early 2024. I haven't worked on it since then so it's dated. There are now better versions of all the models I used. I was able to conversational latency…
I did a MLX "streaming ASR + LLM + streaming TTS" pipeline in early 2024. I haven't worked on it since then so it's dated. There are now better versions of all the models I used. I was able to conversational latency…