A May 5, 2026 announcement presents an initial beta checkpoint for automatic speech recognition and notes a known limitation: support for non-verbal tags is not yet stable.
On May 5, 2026, Qwen3-ASR-Enhanced v0.1 was announced as an initial beta checkpoint for automatic speech recognition (ASR). The announcement says support for non-verbal tags is not yet stable and that a revised version is planned.
Engineers evaluating ASR models can track this initial checkpoint while taking the reported limitation into account. To check the details and any updates, consult the original announcement and verify whether the revised version has been released; the material gives no date for that revision.