| Why does this model only generate audio content lasting more than 20 seconds when processing a 2-minute WAV audio file? | xwang99 | open | 0 | disc |
| Use Qwen3-ASR with FunASR toolkit (one-line setup, speaker diarization) | langgz | open | 0 | disc |
| Endless repetition in output | andypotato | open | 0 | disc |
| Does Qwen3-ASR-1.7B support hotword biasing like Fun-ASR-Nano-2512? | niwang66 | open | 0 | disc |
| Dose Qwen3-ASR-1.7B support hotwords | niwang66 | closed | 0 | disc |
| Add Open ASR Leaderboard evaluation results | SaylorTwift | open | 0 | disc |
| How to specify ASR output language when using vllm serve? | ast980 | open | 0 | disc |
| 为什么一直提示更新transformers,更新了也提示transformers! | Arbatel | open | 0 | disc |
| Is there the option to disable ITN? | kevinq17 | open | 0 | disc |
| just want to drop hi | crypthine | open | 0 | disc |
| Running the example code will cause a shape error，use GPU of 平头哥 | LiuHeiGood | closed | 0 | disc |
| Upload file_00000000bca871fa98b012d07c4aa797.png | Simpkrish | open | 0 | disc |
| How to transcribe the dialect ? | jychan | open | 0 | disc |
| Funasr-api: Production-ready Qwen3-ASR with 52-language support! | pengzhi27 | open | 0 | disc |
| Qwen3-ASR ComfyUI integration | 1038lab | open | 0 | disc |
| Context + Inverse text normalization (ITN)? | Renzust | open | 0 | disc |
| 能像whisper的word_timestamps=False那样输出整个句子的timestamp吗？ | smartsl | open | 0 | disc |
| chatllm.cpp supports Qwen3-ASR models | J22 | open | 0 | disc |
| Improve model card with metadata, paper links, and sample usage | nielsr | open | 0 | disc |
| Any plan to open the streaming model to run without vLLM? | nenad1002 | open | 0 | disc |
| Transformer version error | AhuNorton | open | 0 | disc |
| Update README | MihaiPopa-1 | merged | 0 | disc |
| Lack Of Task Tag | MihaiPopa-1 | open | 0 | disc |
| Timestamp accuracy seems like a mess | Bubblemint | open | 0 | disc |
| Combined Model Suggestion | yukiarimo | open | 0 | disc |