ASR-Next
An audio understanding model from the Qwen team that extends beyond conventional speech recognition. It supports multi-speaker recognition, emotion understanding, sound description, event localization, audio question answering, and audio reasoning.
Timeline (last 90 days)
ASR-Next supports multi-speaker recognition, with speaker labels, timestamps, and aligned transcription text.
ASR-Next can understand emotions, ambient sounds, and machine sounds, enabling sound captioning, event localization, and supporting audio question answering and audio reasoning.
All Facts (2)
ASR-Next supports multi-speaker recognition, with speaker labels, timestamps, and aligned transcription text.
50%UnverifiedASR-Next can understand emotions, ambient sounds, and machine sounds, enabling sound captioning, event localization, and supporting audio question answering and audio reasoning.
50%