zhoukz's picture
Remove system role from example conversation
1fede85 unverified
metadata
license: apache-2.0
language:
  - en
  - zh
  - th
  - id
  - vi
pipeline_tag: audio-text-to-text
tags:
  - multimodal
  - audio-language-model
  - audio
base_model:
  - mispeech/dasheng-0.6B
  - Qwen/Qwen2.5-Omni-7B
base_model_relation: finetune

MiDashengLM-7B-0804 (FP8)

The FP8 weights for mispeech/midashenglm-7b-0804-fp32.

Optimized for Hopper-class (H100 and newer) GPUs, leveraging hardware support for enhanced performance and memory savings. While older GPUs may see limited performance gains, FP8 can still be used to conserve VRAM, and storage.

Usage

Load Model

from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer

model_id = "mispeech/midashenglm-7b-0804-fp8"
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."]

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},
}