test.py

from transformers import Qwen3OmniMoeThinkerForConditionalGeneration, Qwen3OmniMoeProcessor
from qwen_omni_utils import process_mm_info
import torch

model_path = "./"
model = Qwen3OmniMoeThinkerForConditionalGeneration.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    attn_implementation="sdpa",
)
processor = Qwen3OmniMoeProcessor.from_pretrained(model_path)


conversation = [
    {
    "role": "system",
    "content": [
        {"type": "text", "text": "You are a speech recognition model."}
        #{"type": "text", "text": "You are a helpful assistant."}
    ],
    },
    {
        "role": "user",
        "content": [
            {"type": "audio", "audio": "test.wav"},
            {"type": "text", "text": "Transcribe the audio into text."},
        ],
    },
]

# set use audio in video
USE_AUDIO_IN_VIDEO = False

# Preparation for inference
text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
audios, images, videos = process_mm_info(conversation, use_audio_in_video=USE_AUDIO_IN_VIDEO)
#print("audios: ", len(audios[0]) / 16000, text)
inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", padding=True, use_audio_in_video=USE_AUDIO_IN_VIDEO)
inputs = inputs.to(model.device).to(model.dtype)

text_ids = model.generate(**inputs, temperature=0.01)

text = processor.batch_decode(text_ids[:, inputs["input_ids"].shape[1] :],
                              skip_special_tokens=True,
                              clean_up_tokenization_spaces=False)
print(text)