| --- |
| library_name: transformers |
| pipeline_tag: audio-text-to-text |
| license: apache-2.0 |
| tags: |
| - audio |
| - multimodal |
| - robobrain |
| - openmoss-audio |
| --- |
| |
| # GaussianMind |
|
|
| GaussianMind is an audio-language model developed based on RoboBrain and OpenMOSS Audio. |
|
|
| This model is the result of joint research by Hao Tang's team at the School of Computer Science, Peking University, and the Beijing Academy of Artificial Intelligence (BAAI). |
|
|
| ## Usage |
|
|
| The repository includes custom Transformers code. Load the model and processor with `trust_remote_code=True`: |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoProcessor |
| |
| model_id = "BAAI/GaussianMind" |
| processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True) |
| model = AutoModelForCausalLM.from_pretrained( |
| model_id, |
| trust_remote_code=True, |
| device_map="auto", |
| ) |
| ``` |
|
|
| ## Acknowledgements |
|
|
| GaussianMind builds upon RoboBrain and OpenMOSS Audio. We thank their contributors for making this work possible. |
|
|
