GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

This is the official implementation of our paper GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities.

Updates 🚨

• 🎉 GAMA achieves the highest F1 score amongst all LALMs on Deductive Reasoning benchmark by Microsoft (Table 4; ACE F1 and NACC)!
• 🎉 GAMA achieves the highest F1/Accuracy score amongst all LALMs on Audio Hallucination benchmark by NTU! A staggering 81.7% on POPE for Random and w/ Sampling.

Demo

We have hosted 2 HF spaces, generously supported by HuggingFace🤗 for GAMA and GAMA-IT. Feel free to play around with our models here:

      

Resources

All resources required for GAMA and GAMA-IT can be found in this drive. Information about the files is provided below in respective sections. We also share some additional CLAP Checkpoints (to be used with this repository) to promote research in this space. These CLAP checkpoints are trained on 2M+ audio-caption pairs with large batch sizes on H100s.

Setup 🏋️

conda create -n gama python=3.10
conda activate gama
pip install -r requirements.txt
pip install -e hf-dev-train/transformers-main
pip install -e peft-main

---

Training 🏃‍♂️

When preparing audio files, please make sure all audio files use the same sampling rate of 16kHz.

The format of the dataset is a JSON file of a list of dicts, in the following format:

[
 {
  "audio_id": "path_to_audio_file",
  "instruction": "Question",
  "dataset": "dataset_name", % (optional)
  "task": "type_of_task", % question type (optional)
  "output": "corect_answer"
 },
  ...
]

• Download the Llama-2-7b-chat-hf-qformer from here.
• Update the path of the dowloaded Llama-2-7b-chat-hf-qformer in finetune.py on line 93 and 98.

Use the following commands to train the model:

conda activate gama
cd train_script
# run finetuning on the data to train GAMA
./stage1.sh # need to specify the path of Llama-2-7b-chat-hf-qformer in for the `--base_model` arg.
./stage2.sh # need to specify the checkpoint in stage 1 training
./stage3.sh # need to specify the checkpoint in stage 2 training
./stage4.sh # need to specify the checkpoint in stage 3 training
# to instruction tune GAMA
./stage5.sh # need to specify the checkpoint in stage 4 training

To infer or instruction tune GAMA on your own dataset, we have provided the checkpoints for stage 4 and stage 5 here.

---

Inference of GAMA 🔖

To infer GAMA/GAMA-IT on CompA-R benchmark, change the path to model in gama_inf.py on line 215, and run:

python gama_inf.py

• CompA-R audios can be downloaded from here.

Evaluation

To evaluate GAMA we use the evaluation scheme employed by LTU, the evaluation scripts can be found here.

---

Note: The current code of GAMA does not include the implementation of soft-prompt. The code for soft-prompt (and its related checkpoints) will be released after the paper is accepted. However, the stage 5 checkpoint released currently performs almost as well as with soft-prompt.

---

Acknowledgement 🌻

We would like to thank the authors of LTU for open-sourcing their code, which inspired our work.

Citation 🔏

@misc{ghosh2024gamalargeaudiolanguagemodel,
      title={GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities}, 
      author={Sreyan Ghosh and Sonal Kumar and Ashish Seth and Chandra Kiran Reddy Evuru and Utkarsh Tyagi and S Sakshi and Oriol Nieto and Ramani Duraiswami and Dinesh Manocha},
      year={2024},
      eprint={2406.11768},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2406.11768}, 
}