Please, star our project on github (see top-right corner) if you appreciate our contribution to the community!

Welcome to the SpeechBrain Benchmarks repository! This repository is dedicated to housing a collection of benchmarks associated with the SpeechBrain toolkit.

What are benchmarks? Benchmarks are standardized sets of recipes that enable users to measure the performance of specific models or techniques within a standardized environment. By utilizing these benchmarks, you can evaluate and compare the effectiveness of different approaches.

The SpeechBrain Benchmarks currently include the following:

• CL_MASR - A benchmark designed to assess continual learning techniques, specifically focusing on the continual learning of new languages for speech recognition.

• MP3S - A benchmark created to facilitate the fair assessment of self-supervised speech representations.

Our benchmarks align with speechbrain's commitment to transparent and replicable research by providing standardized tools and resources for studying specific topics.

To learn more about each available benchmark, please click on the corresponding link provided above. We encourage you to explore the benchmarks and utilize them for your research and experimentation.

If you have any questions or need assistance, please don't hesitate to reach out. Happy benchmarking!

Please, cite SpeechBrain if you use it for your research or business.

@misc{speechbrain,
  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}