PulseAugur
EN
LIVE 02:22:26
中文(ZH) 千问大模型升级实时语音识别大模型Fun-ASR-Realtime

Qwen Large Model upgrades to real-time speech recognition model Fun-ASR-Realtime

Qwen Large Model has upgraded its real-time speech recognition model to Fun-ASR-Realtime. This new model boasts a latency of under 100 milliseconds for the first character and achieves accuracy close to offline models. It supports recognition in 16 dialects and 30 languages. AI

IMPACT This upgrade enhances real-time speech processing capabilities, potentially improving user interaction and accessibility for AI applications.

RANK_REASON This is an upgrade to a specific component of a large language model, not a new frontier model release.

Read on 36氪 (36Kr) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Qwen Large Model upgrades to real-time speech recognition model Fun-ASR-Realtime

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is an upgrade to a specific component of a large language model, not a new frontier model release.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
94 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. 36氪 (36Kr) TIER_1 中文(ZH) ·

    Qwen Large Model Upgrades Real-time Speech Recognition Large Model Fun-ASR-Realtime

    36氪获悉,千问大模型正式升级实时语音识别大模型Fun-ASR-Realtime——一款首字延迟控制在百毫秒级别、识别准确率接近离线模型的流式语音识别模型,支持16种方言和30种语言。