from transformers import AutoModelForCausalLM, AutoTokenizer model_id = 'Aye10032/Qwen3-ASR-Refiner-4B'tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype='auto', device_map='auto') messages = [ { 'role': 'system', 'content': '将中文口语转写改写为正式、自然的书面语。保持原意,不添加原文没有的信息,只输出改写后的文本。', }, {'role': 'user', 'content': '呃这个事情吧我们之后再讨论一下。'},]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(text, return_tensors='pt').to(model.device)outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)answer = tokenizer.decode(outputs[0, inputs.input_ids.shape[1]:], skip_special_tokens=True)print(answer)