MiDashengLM-7B-0804 - A general audio captioner

MiDashengLM is an efficient audio-language model that achieves holistic audio understanding through caption-based alignment. It achieves state-of-the-art performance on multiple audio understanding benchmarks while maintaining high inference efficiency—delivering 3.2× throughput speedup and supporting batch sizes up to 512.

📖 For more detailed introduction and technical report, please visit our GitHub repository.

Note that for most applications, we strongly recommend using the BF16 version (mispeech/midashenglm-7b-0804-bf16) for optimal performance and efficiency.

Usage

Load Model

from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer

model_id = "mispeech/midashenglm-7b-0804-fp32"  # Only for exact reproduction; otherwise strongly recommend "mispeech/midashenglm-7b-0804-bf16"
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

Construct Prompt

user_prompt = "Caption the audio."  # You may try any other prompt

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": user_prompt},
            {
                "type": "audio",
                "path": "/path/to/example.wav",
                # or "url": "https://example.com/example.wav"
                # or "audio": np.random.randn(16000)
            },
        ],
    },
]

Generate Output

import torch

with torch.no_grad():
    model_inputs = processor.apply_chat_template(
        messages,
        tokenize=True,
        add_generation_prompt=True,
        add_special_tokens=True,
        return_dict=True,
    ).to(device=model.device, dtype=model.dtype)
    generation = model.generate(**model_inputs)
    output = tokenizer.batch_decode(generation, skip_special_tokens=True)  # ["An engine is idling."]

Results

The following evaluation results are based on the model version: mispeech/midashenglm-7b-0804-fp32.

Audio Captioning Results

Metrics: FENSE (higher is better).

Audio and Paralinguistic Classification

ASR Performance

Metrics: WER/CER (lower is better).

Question Answering Results

Metrics: Higher is better.

Citation

MiDashengLM is under the Apache License 2.0, and we encourage its use in both research and business applications.

If you find MiDashengLM useful in your research, please consider citing our work:

@techreport{midashenglm7b,
  title      = {MiDashengLM: Efficient Audio Understanding with General Audio Captions},
  author     = {{Horizon Team, MiLM Plus}},
  institution= {Xiaomi Inc.},
  year       = {2025},
  note       = {Contributors: Heinrich Dinkel et al. (listed alphabetically in Appendix B)},
  url        = {https://arxiv.org/abs/2508.03983},
  eprint     = {2508.03983},
}