Audio-text Model¶

Number of models: 10

Instruction Model¶

`LCO-Embedding/LCO-Embedding-Omni-3B`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
32.8K	2048	4.7B	8.8 GB	2025-10-23	eng-Latn

Citation

@misc{xiao2025scalinglanguagecentricomnimodalrepresentation,
  title={Scaling Language-Centric Omnimodal Representation Learning},
  author={Chenghao Xiao and Hou Pong Chan and Hao Zhang and Weiwen Xu and Mahani Aljunied and Yu Rong},
  year={2025},
  eprint={2510.11693},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2510.11693},
}

`LCO-Embedding/LCO-Embedding-Omni-7B`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
32.8K	3584	8.9B	16.6 GB	2025-10-15	eng-Latn

Citation

@misc{xiao2025scalinglanguagecentricomnimodalrepresentation,
  title={Scaling Language-Centric Omnimodal Representation Learning},
  author={Chenghao Xiao and Hou Pong Chan and Hao Zhang and Weiwen Xu and Mahani Aljunied and Yu Rong},
  year={2025},
  eprint={2510.11693},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2510.11693},
}

`Qwen/Qwen2-Audio-7B`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
131.1K	1280	7.0B	not specified	2024-08-09	eng-Latn

Citation

@misc{chu2024qwen2audiotechnicalreport,
      title={Qwen2-Audio Technical Report},
      author={Yunfei Chu and Jin Xu and Qian Yang and Haojie Wei and Xipin Wei and Zhifang Guo and Yichong Leng and Yuanjun Lv and Jinzheng He and Junyang Lin and Chang Zhou and Jingren Zhou},
      year={2024},
      eprint={2407.10759},
      archivePrefix={arXiv},
      primaryClass={eess.AS},
      url={https://arxiv.org/abs/2407.10759},
}

Non-instruction Model¶

`OpenMuQ/MuQ-MuLan-large`¶

License: cc-by-nc-4.0

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
not specified	512	630.0M	2.5 GB	2025-01-01	eng-Latn, zho-Hans

Citation

@misc{zhu2025muqselfsupervisedmusicrepresentation,
  title={MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization},
  author={Haina Zhu and Yizhi Zhou and Hangting Chen and Jianwei Yu and Ziyang Ma and Rongzhi Gu and Yi Luo and Wei Tan and Xie Chen},
  year={2025},
  eprint={2501.01108},
  archivePrefix={arXiv},
  primaryClass={cs.SD},
  url={https://arxiv.org/abs/2501.01108},
}

`laion/clap-htsat-fused`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
infP	512	153.5M	586.0 MB	2023-05-22	eng-Latn

Citation

@misc{wu2024largescalecontrastivelanguageaudiopretraining,
      title={Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
      author={Yusong Wu and Ke Chen and Tianyu Zhang and Yuchen Hui and Marianna Nezhurina and Taylor Berg-Kirkpatrick and Shlomo Dubnov},
      year={2024},
      eprint={2211.06687},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2211.06687},
}

`laion/clap-htsat-unfused`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
infP	512	153.5M	586.0 MB	2023-05-22	eng-Latn

Citation

@misc{wu2024largescalecontrastivelanguageaudiopretraining,
      title={Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
      author={Yusong Wu and Ke Chen and Tianyu Zhang and Yuchen Hui and Marianna Nezhurina and Taylor Berg-Kirkpatrick and Shlomo Dubnov},
      year={2024},
      eprint={2211.06687},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2211.06687},
}

`laion/larger_clap_general`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
infP	512	193.9M	740.0 MB	2023-05-22	eng-Latn

Citation

@misc{wu2024largescalecontrastivelanguageaudiopretraining,
      title={Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
      author={Yusong Wu and Ke Chen and Tianyu Zhang and Yuchen Hui and Marianna Nezhurina and Taylor Berg-Kirkpatrick and Shlomo Dubnov},
      year={2024},
      eprint={2211.06687},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2211.06687},
}

`laion/larger_clap_music`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
infP	512	193.9M	740.0 MB	2023-05-22	eng-Latn

Citation

@misc{wu2024largescalecontrastivelanguageaudiopretraining,
      title={Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
      author={Yusong Wu and Ke Chen and Tianyu Zhang and Yuchen Hui and Marianna Nezhurina and Taylor Berg-Kirkpatrick and Shlomo Dubnov},
      year={2024},
      eprint={2211.06687},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2211.06687},
}

`laion/larger_clap_music_and_speech`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
infP	512	193.9M	740.0 MB	2023-05-22	eng-Latn

Citation

@misc{wu2024largescalecontrastivelanguageaudiopretraining,
      title={Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
      author={Yusong Wu and Ke Chen and Tianyu Zhang and Yuchen Hui and Marianna Nezhurina and Taylor Berg-Kirkpatrick and Shlomo Dubnov},
      year={2024},
      eprint={2211.06687},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2211.06687},
}

`lyrebird/wav2clip`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
not specified	512	163.0M	622.0 MB	2022-03-15	eng-Latn

Citation

@misc{wu2022wav2cliplearningrobustaudio,
  title={Wav2CLIP: Learning Robust Audio Representations From CLIP},
  author={Ho-Hsiang Wu and Prem Seetharaman and Kundan Kumar and Juan Pablo Bello},
  year={2022},
  eprint={2110.11499},
  archivePrefix={arXiv},
  primaryClass={cs.SD},
  url={https://arxiv.org/abs/2110.11499},
}

`microsoft/msclap-2022`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
not specified	1024	196.0M	750.0 MB	2022-12-01	eng-Latn

Citation

@inproceedings{CLAP2022,
  title={Clap learning audio concepts from natural language supervision},
  author={Elizalde, Benjamin and Deshmukh, Soham and Al Ismail, Mahmoud and Wang, Huaming},
  booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={1--5},
  year={2023},
  organization={IEEE}
}

`microsoft/msclap-2023`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
not specified	1024	160.0M	610.0 MB	2023-09-01	eng-Latn

Citation

@misc{CLAP2023,
      title={Natural Language Supervision for General-Purpose Audio Representations},
      author={Benjamin Elizalde and Soham Deshmukh and Huaming Wang},
      year={2023},
      eprint={2309.05767},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2309.05767}
}

`microsoft/speecht5_multimodal`¶

License: mit

Max Tokens	Embedding dimension	Parameters	Required Memory (Mb)	Release date	Languages
not specified	768	297.9M	1.1 GB	2022-05-16	eng-Latn

Citation

@misc{ao2022speecht5unifiedmodalencoderdecoderpretraining,
      title={SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing},
      author={Junyi Ao and Rui Wang and Long Zhou and Chengyi Wang and Shuo Ren and Yu Wu and Shujie Liu and Tom Ko and Qing Li and Yu Zhang and Zhihua Wei and Yao Qian and Jinyu Li and Furu Wei},
      year={2022},
      eprint={2110.07205},
      archivePrefix={arXiv},
      primaryClass={eess.AS},
      url={https://arxiv.org/abs/2110.07205},
}