GLAP (Generalized Language Audio Pretraining)

Official PyTorch code for GLAP
Generalized Language Audio Pretraining

GLAP (Generalized Language Audio Pretraining)

Features

• First all-in-one solution for general audio-text retrieval.
• Multilingual (8 + Languages) Speech, Music and Sound retrieval.
• Music and Sound retrieval performance in English matches previous baselines, while also supporting Languages like Japanese, German, Spanish, Chinese, Dutch and more.

Usage

pip install glap_model

Scoring audio-text pairs

We provide a simple commandline tool:

score_glap audio_input_file text1;text2;text3

Or in Python:

import torch
from glap_model import glap_inference

audio = torch.randn(1, 160000).tanh() # 10s of heavy noise

glap_model = glap_inference()

score = glap_model.score_forward(audio, text=["the sound of noise","a car is driving","a person is speaking"])
print(score)

Recommended Prompts

Task	Prompt
Speech	{label}
Music	The music in the style of {label}.
Sound	The sound of {label} can be heard.

Embedding extraction

import torch
from glap_model import glap_inference

glap_model = glap_inference()
audio:torch.Tensor = torch.randn(1, 64000).tanh()
prefix = "The sound of"
text_data:List[str] = [ f"{prefix} {label}" for label in ("Cat","Dog","Water","Noise")]
text_embeds = glap_model.encode_text(text_data)
audio_embeds = glap_model.encode_audio(audio)

Batched scoring

import torch
from glap_model import glap_inference

glap_model = glap_inference()
audio = torch.randn(1, 64000).tanh()
prefix = "The sound of"
labels = [ f"{prefix} {label}" for label in ("Cat","Dog","Water","Noise")]
text_embeds = glap_model.encode_text(labels)
audio_embeds = glap_model.encode_audio(audio)
scores = glap_model.score(audio_embeds, text_embeds)
for label_name, score in zip(labels, scores):
  print(label_name,score)

Development

UV (Recommended)

git clone https://github.com/xiaomi-research/dasheng-glap
cd GLAP
uv venv --python 3.10
source activate .venv/bin/activate
uv sync

#python3 -m pip install .
# Additionally, sndfile is needed
# conda install -c conda-forge libsndfile==1.0.31

Pip

git clone https://github.com/xiaomi-research/dasheng-glap
cd GLAP
python3 -m pip install .
# Additionally, sndfile is needed
# conda install -c conda-forge libsndfile==1.0.31
# Or if you have root, use your package manager

Prepare data

Data needs to be in tar/tar.gz format:

   # tar -tf a.tar
908-31957-0013.flac
908-31957-0013.json
2961-960-0013.flac
2961-960-0013.json

Each .json should have one of three fields caption, captions or text. Data preparation can be done using the wavlist_to_tar script, which is provided in the dasheng dependency. Further information how to process data can be seen here.

Training

For reference, we provide our original training config for GLAP configs/train/multilingual_dasheng_asr_sound2_sigmoidloss_balanced.yaml.

accelerate launch --mixed-precision='fp16' run.py train configs/train/multilingual_dasheng_asr_sound2_sigmoidloss_balanced.yaml

Zeroshot eval (one sample)

# There ; is a separator for different text keys
python3 run.py zeroshot pretrained_checkpoint/glap_checkpoint.pt PATH_TO_WAV_FLAC_MP3_SAMPLE.wav "The sound of a horse;Car;Mama;The sound of music;somebody is speaking;The sound of ein Pferd;一只马;Music is played;音乐的声音;Musik ist zu hoeren";Zero;One;Two;Three"

Retrieval scoring

# Should be run on a single GPU
accelerate launch --mixed-precision='fp16' run.py evaluate PATH_TO_CHECKPOINT

Notes on DDP

Using uneven training datasets without resample=True is not recommended

Translating data into a target language

For our experiments we used SONAR to translate audio captions into seven target languages. This can be reproduced using our code:

python3 run.py translate_sonar data/WavCaps/freesound/freesound_train_sample_0000* --output_path data/translations/WavCaps/freesound/

DDP is also supported:

accelerate launch run.py translate_sonar  data/WavCaps/freesound/freesound_train_sample_0000* --output_path data/translations/WavCaps/freesound/

Citation

@misc{2506.11350,
Author = {Heinrich Dinkel and Zhiyong Yan and Tianzi Wang and Yongqing Wang and Xingwei Sun and Yadong Niu and Jizhong Liu and Gang Li and Junbo Zhang and Jian Luan},
Title = {GLAP: General contrastive audio-text pretraining across domains and languages},
Year = {2025},
Eprint = {arXiv:2506.11350},
}