[Model] Add transcription support for Qwen3-Omni (#29828)

Signed-off-by: Muhammad Hashmi <mhashmi@berkeley.edu>
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
This commit is contained in:
Muhammad Hashmi
2026-02-04 21:17:47 +00:00
committed by GitHub
co-authored by NickLucche
parent 4292c90a2a
commit 535de06cb1
3 changed files with 104 additions and 2 deletions
+1
View File
@@ -251,6 +251,7 @@ No extra registration is required beyond having your model class available via t
- Whisper encoder–decoder (audio-only): [vllm/model_executor/models/whisper.py](../../../vllm/model_executor/models/whisper.py)
- Voxtral decoder-only (audio embeddings + LLM): [vllm/model_executor/models/voxtral.py](../../../vllm/model_executor/models/voxtral.py). Make sure to have installed `mistral-common[audio]`.
- Gemma3n decoder-only with fixed instruction prompt: [vllm/model_executor/models/gemma3n_mm.py](../../../vllm/model_executor/models/gemma3n_mm.py)
- Qwen3-Omni multimodal with audio embeddings: [vllm/model_executor/models/qwen3_omni_moe_thinker.py](../../../vllm/model_executor/models/qwen3_omni_moe_thinker.py)
## Test with the API
+1
View File
@@ -781,6 +781,7 @@ Speech2Text models trained specifically for Automatic Speech Recognition.
| `GlmAsrForConditionalGeneration` | GLM-ASR | `zai-org/GLM-ASR-Nano-2512` | ✅︎ | ✅︎ |
| `GraniteSpeechForConditionalGeneration` | Granite Speech | `ibm-granite/granite-speech-3.3-2b`, `ibm-granite/granite-speech-3.3-8b`, etc. | ✅︎ | ✅︎ |
| `Qwen3ASRForConditionalGeneration` | Qwen3-ASR | `Qwen/Qwen3-ASR-1.7B`, etc. | | ✅︎ |
| `Qwen3OmniMoeThinkerForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct`, etc. | | ✅︎ |
| `VoxtralForConditionalGeneration` | Voxtral (Mistral format) | `mistralai/Voxtral-Mini-3B-2507`, `mistralai/Voxtral-Small-24B-2507`, etc. | ✅︎ | ✅︎ |
| `WhisperForConditionalGeneration` | Whisper | `openai/whisper-small`, `openai/whisper-large-v3-turbo`, etc. | | |