Today Qianwen upgraded its real-time speech-recognition model Fun-ASR-Realtime, a streaming ASR system with first-word latency controlled at the hundred-millisecond level and recognition accuracy approaching offline models; it supports 16 dialects an

2026-07-06

Today Qianwen upgraded its real-time speech-recognition model Fun-ASR-Realtime, a streaming ASR system with first-word latency controlled at the hundred-millisecond level and recognition accuracy approaching offline models; it supports 16 dialects and 30 languages.