SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training
This is the pretrained model of
SPIRAL Base with Multi-Condition Training
, trained with 960-hour LibriSpeech data, and noise dataset from
ICASSP 2021 DNS Challenge
for noise robustness.
Citation
If you find SPIRAL useful in your research, please cite the following paper:
@inproceedings{huang2022spiral,
title={{SPIRAL}: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training},
author={Wenyong Huang and Zhenhe Zhang and Yu Ting Yeung and Xin Jiang and Qun Liu},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=TBpg4PnXhYH}
}
Runs of huawei-noah SPIRAL-base-MCT on huggingface.co
0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About SPIRAL-base-MCT huggingface.co Model
SPIRAL-base-MCT huggingface.co
SPIRAL-base-MCT huggingface.co is an AI model on huggingface.co that provides SPIRAL-base-MCT's model effect (), which can be used instantly with this huawei-noah SPIRAL-base-MCT model. huggingface.co supports a free trial of the SPIRAL-base-MCT model, and also provides paid use of the SPIRAL-base-MCT. Support call SPIRAL-base-MCT model through api, including Node.js, Python, http.
SPIRAL-base-MCT huggingface.co is an online trial and call api platform, which integrates SPIRAL-base-MCT's modeling effects, including api services, and provides a free online trial of SPIRAL-base-MCT, you can try SPIRAL-base-MCT online for free by clicking the link below.
huawei-noah SPIRAL-base-MCT online free url in huggingface.co:
SPIRAL-base-MCT is an open source model from GitHub that offers a free installation service, and any user can find SPIRAL-base-MCT on GitHub to install. At the same time, huggingface.co provides the effect of SPIRAL-base-MCT install, users can directly use SPIRAL-base-MCT installed effect in huggingface.co for debugging and trial. It also supports api for free installation.