Instructions to use Aye10032/Qwen3-ASR-Refiner-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aye10032/Qwen3-ASR-Refiner-4B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Aye10032/Qwen3-ASR-Refiner-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aye10032/Qwen3-ASR-Refiner-4B")
model = AutoModelForCausalLM.from_pretrained("Aye10032/Qwen3-ASR-Refiner-4B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aye10032/Qwen3-ASR-Refiner-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aye10032/Qwen3-ASR-Refiner-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aye10032/Qwen3-ASR-Refiner-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aye10032/Qwen3-ASR-Refiner-4B

SGLang

How to use Aye10032/Qwen3-ASR-Refiner-4B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Aye10032/Qwen3-ASR-Refiner-4B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aye10032/Qwen3-ASR-Refiner-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Aye10032/Qwen3-ASR-Refiner-4B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aye10032/Qwen3-ASR-Refiner-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aye10032/Qwen3-ASR-Refiner-4B with Docker Model Runner:
```
docker model run hf.co/Aye10032/Qwen3-ASR-Refiner-4B
```

Qwen3 ASR Refiner

Qwen3 ASR Refiner is a family of models that converts Chinese ASR transcripts and other spoken-style text into concise, natural written Chinese while preserving the original meaning. All variants are fine-tuned on Aye10032/WenetSpeech-Formal-Text with the same task definition and training recipe.

Model family

Variant	Base model	Model repository
0.6B	`Qwen/Qwen3-0.6B`	`Aye10032/Qwen3-ASR-Refiner-0.6B`
1.7B	`Qwen/Qwen3-1.7B`	`Aye10032/Qwen3-ASR-Refiner-1.7B`
4B	`Qwen/Qwen3-4B`	`Aye10032/Qwen3-ASR-Refiner-4B`

The LoRA adapter has been merged into the base model. This repository contains complete BF16 Transformers weights and can be loaded directly without PEFT.

Usage

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)