AK(@_akhaliq):Audio8 ASR Infinite streaming speech recognition model the native streaming architecture decodes 12.5 times per second a rolling KV Cache keeps both memory and latency constant, even in 24/7 operation one text token per clock step (12.5 / 8.3 / 6.25 decisions per second), balancing perception granularity and resource cost ML intern in huggingchat setup a gradio workflow to try it out: https://t.co/6OB6nG0Rog huggingchat: https://t.co/C0TsUhOgmp model:

@_akhaliq

AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo ,submit papers here:

参加 April 2014

3.1K フォロー中 529.2K ファン

AK@_akhaliq

2026.09.30 03:32

Audio8 ASR Infinite streaming speech recognition model the native streaming architecture decodes 12.5 times per second a rolling KV Cache keeps both memory and latency constant, even in 24/7 operation one text token per clock step (12.5 / 8.3 / 6.25 decisions per second), balancing perception granularity and resource cost ML intern in huggingchat setup a gradio workflow to try it out: huggingchat: model: