Primary sourceGorden Sun
View sourceEvent ·Single source
Edge0开源Audio8-ASR-Infinite：中英文流式语音识别模型，支持7x24小时不间断转写
Edge0开源了流式语音识别模型Audio8-ASR-Infinite，支持中英双语，转写延迟低至几百毫秒。模型采用循环滑动缓存机制，使计算延迟和显存占用保持恒定，避免长音频转写时的漂移和内存溢出问题。内置语义活动检测，能识别真实停顿、结巴与说话结束。该模型适合长时间直播听写和高响应实时语音交互场景，支持7x24小时不间断运行。
Current read
Edge0开源的流式语音识别模型，中英文都能转，延迟几百毫秒，显存占用恒定不爆内存，直播听写可以直接跑起来。
2 sources73° AI heatLast updated 2026/9/25 15:19:45
Evidence
2 sourcesRelated source 1AI Will
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.