arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2406.06371cs.CLcs.SDeess.AS

mHuBERT-147:一个紧凑的多语言HuBERT模型

mHuBERT-147: A Compact Multilingual HuBERT Model

NAVER LABS Europe(NAVER欧洲实验室);University of Edinburgh(爱丁堡大学)

Marcely Zanon Boito, Vivek Iyer, Nikolaos Lagos, Laurent Besacier, Ioan Calapodescu

AI总结:

本文提出mHuBERT-147,一个在9万小时开放数据上训练、仅9500万参数的紧凑多语言HuBERT模型,通过faiss聚类加速和多语言上采样策略,在ML-SUPERB等基准上超越更大模型,实现性能与参数效率的平衡。

摘要:

我们提出mHuBERT-147,这是第一个通用的大规模多语言HuBERT语音表示模型,在9万小时干净、开放许可的数据上训练。为了扩展多迭代HuBERT方法,我们使用基于faiss的聚类,实现比原始方法快5.2倍的标签分配。我们还应用了一种新的多语言批处理上采样策略,同时利用语言和数据集多样性。经过3轮训练迭代,我们紧凑的9500万参数mHuBERT-147优于在显著更多数据上训练的更大模型。我们在ML-SUPERB 10分钟和1小时排行榜上分别排名第二和第一,并在3项任务上取得SOTA分数。在ASR/LID任务中,我们的模型始终超越XLS-R(3亿参数;43.6万小时),并展现出与更大的MMS(10亿参数;49.1万小时)相比的强大竞争力。我们的发现表明,mHuBERT-147是一个有前景的多语言语音任务模型,在高性能和参数效率之间提供了前所未有的平衡。

英文摘要:

We present mHuBERT-147, the first general-purpose massively multilingual HuBERT speech representation model trained on 90K hours of clean, open-license data. To scale up the multi-iteration HuBERT approach, we use faiss-based clustering, achieving 5.2x faster label assignment than the original method. We also apply a new multilingual batching up-sampling strategy, leveraging both language and dataset diversity. After 3 training iterations, our compact 95M parameter mHuBERT-147 outperforms larger models trained on substantially more data. We rank second and first on the ML-SUPERB 10min and 1h leaderboards, with SOTA scores for 3 tasks. Across ASR/LID tasks, our model consistently surpasses XLS-R (300M params; 436K hours) and demonstrates strong competitiveness against the much larger MMS (1B params; 491K hours). Our findings indicate that mHuBERT-147 is a promising model for multilingual speech tasks, offering an unprecedented balance between high performance and parameter efficiency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑