Qwen Unveils Real-Time Speech Recognition Model Fun-ASR-Realtime

Speech interaction is undergoing a new technological breakthrough. Recently, the Qwen large model announced an upgrade to its core audio capabilities, introducing a new real-time speech recognition model named Fun-ASR-Realtime.
The model achieves significant performance breakthroughs, with first-character recognition delay precisely controlled within the hundred-millisecond range, providing users with a smooth "speak and receive immediate feedback" experience. Its accuracy is excellent, approaching the level of industry-leading offline models, effectively combining real-time performance with high quality.
To address diverse application needs, Fun-ASR-Realtime provides extensive language coverage. It supports recognition and processing of up to 30 languages, with special enhancements for understanding Chinese dialects—currently capable of handling complex voice inputs in 16 dialects.
This upgrade not only provides stronger underlying support for real-time interaction scenarios like voice assistants and meeting notes, but also expands the application boundaries of general large models in multilingual and multi-dialect environments. With the model's official launch, developers and enterprise users can more easily build intelligent voice applications with high sensitivity and accuracy, making AI interactions more natural and human-like.
Related article
DeepMind CEO Hassabis: I sleep six hours a day, usually feel energetic around 1 a.m.
Fortune recently featured an interview with Demis Hassabis, CEO of Google DeepMind, revealing his unconventional approach to rest and productivity. Hassabis disclosed that he sleeps very little, structuring his waking hours into two distinct work blo
OpenAI, Anthropic Vie for Market Share Despite Revenue Shortfalls
Despite recent reports suggesting OpenAI missed revenue targets, creating pressure on tech stocks this Tuesday, private AI lab investors remain resilient. Seasoned backers have confirmed they will not reduce investment despite negative media coverage
California AV Compliance: A New Era of Tickets, Geofences, and 1M Miles
Guident operates an AuveTech shuttle in South Florida, managing a four-mile route in West Palm Beach and a one-mile route in Boca Raton using its remote monitoring technology. | Credit: GuidentCalifornia is redefining the regulatory landscape for dri
Related Special Topic Recommendations
Comments (0)
0/500

Speech interaction is undergoing a new technological breakthrough. Recently, the Qwen large model announced an upgrade to its core audio capabilities, introducing a new real-time speech recognition model named Fun-ASR-Realtime.
The model achieves significant performance breakthroughs, with first-character recognition delay precisely controlled within the hundred-millisecond range, providing users with a smooth "speak and receive immediate feedback" experience. Its accuracy is excellent, approaching the level of industry-leading offline models, effectively combining real-time performance with high quality.
To address diverse application needs, Fun-ASR-Realtime provides extensive language coverage. It supports recognition and processing of up to 30 languages, with special enhancements for understanding Chinese dialects—currently capable of handling complex voice inputs in 16 dialects.
This upgrade not only provides stronger underlying support for real-time interaction scenarios like voice assistants and meeting notes, but also expands the application boundaries of general large models in multilingual and multi-dialect environments. With the model's official launch, developers and enterprise users can more easily build intelligent voice applications with high sensitivity and accuracy, making AI interactions more natural and human-like.
DeepMind CEO Hassabis: I sleep six hours a day, usually feel energetic around 1 a.m.
Fortune recently featured an interview with Demis Hassabis, CEO of Google DeepMind, revealing his unconventional approach to rest and productivity. Hassabis disclosed that he sleeps very little, structuring his waking hours into two distinct work blo
OpenAI, Anthropic Vie for Market Share Despite Revenue Shortfalls
Despite recent reports suggesting OpenAI missed revenue targets, creating pressure on tech stocks this Tuesday, private AI lab investors remain resilient. Seasoned backers have confirmed they will not reduce investment despite negative media coverage





Home






