Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts

• URL: http://arxiv.org/abs/2311.01070v3
• Date: Tue, 12 Mar 2024 14:50:30 GMT
• Title: Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts
• Authors: Thomas Palmeira Ferraz, Marcely Zanon Boito, Caroline Brun, Vassilina Nikoulina
• Abstract summary: We propose DistilWhisper to bridge the performance gap in ASR for under-represented languages. Our approach involves two key strategies: lightweight modular ASR fine-tuning of whisper-small using language-specific experts, and knowledge distillation from whisper-large-v2. Results demonstrate that our approach is more effective than standard fine-tuning or LoRA adapters.
• Score: 14.999359332108767
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number of under-represented languages, a problem exacerbated in smaller model versions. In this work, we propose DistilWhisper, an approach able to bridge the performance gap in ASR for these languages while retaining the advantages of multitask and multilingual capabilities. Our approach involves two key strategies: lightweight modular ASR fine-tuning of whisper-small using language-specific experts, and knowledge distillation from whisper-large-v2. This dual approach allows us to effectively boost ASR performance while keeping the robustness inherited from the multitask and multilingual pre-training. Results demonstrate that our approach is more effective than standard fine-tuning or LoRA adapters, boosting performance in the targeted languages for both in- and out-of-domain test sets, while introducing only a negligible parameter overhead at inference.

Related papers

• Efficient Compression of Multitask Multilingual Speech Models [0.0]
  DistilWhisper is able to bridge the performance gap in ASR for these languages while retaining the advantages of multitask and multilingual capabilities. Our approach involves two key strategies: lightweight modular ASR fine-tuning of whisper-small using language-specific experts, and knowledge distillation from whisper-large-v2.
  arXiv  Detail & Related papers  (2024-05-02T03:11:59Z)
• Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages [60.162717568496355]
  Large language models (LLMs) have been pre-trained on multilingual corpora. Their performance still lags behind in most languages compared to a few resource-rich languages.
  arXiv  Detail & Related papers  (2024-02-19T15:07:32Z)
• Efficient Spoken Language Recognition via Multilabel Classification [53.662747523872305]
  We show that our models obtain competitive results while being orders of magnitude smaller and faster than current state-of-the-art methods. Our multilabel strategy is more robust to unseen non-target languages compared to multiclass classification.
  arXiv  Detail & Related papers  (2023-06-02T23:04:19Z)
• Adapting Multi-Lingual ASR Models for Handling Multiple Talkers [63.151811561972515]
  State-of-the-art large-scale universal speech models (USMs) show a decent automatic speech recognition (ASR) performance across multiple domains and languages. We propose an approach to adapt USMs for multi-talker ASR. We first develop an enhanced version of serialized output training to jointly perform multi-talker ASR and utterance timestamp prediction.
  arXiv  Detail & Related papers  (2023-05-30T05:05:52Z)
• From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition [50.93943755401025]
  We propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition. We design different auxiliary neural architectures focusing on learnable pre-trained feature enhancement. Our methods outperform existing ASR tuning architectures and their extension with self-supervised losses.
  arXiv  Detail & Related papers  (2023-01-19T02:37:56Z)
• Learning ASR pathways: A sparse multilingual ASR model [31.147484652643282]
  We present ASR pathways, a sparse multilingual ASR model that activates language-specific sub-networks ("pathways") With the overlapping sub-networks, the shared parameters can also enable knowledge transfer for lower-resource languages via joint multilingual training. Our proposed ASR pathways outperform both dense models and a language-agnostically pruned model, and provide better performance on low-resource languages.
  arXiv  Detail & Related papers  (2022-09-13T05:14:08Z)
• Distilling a Pretrained Language Model to a Multilingual ASR Model [3.4012007729454816]
  We distill the rich knowledge embedded inside a well-trained teacher text model to the student speech model. We show the superiority of our method on 20 low-resource languages of the CommonVoice dataset with less than 100 hours of speech data.
  arXiv  Detail & Related papers  (2022-06-25T12:36:11Z)
• Adaptive Activation Network For Low Resource Multilingual Speech Recognition [30.460501537763736]
  We introduce an adaptive activation network to the upper layers of ASR model. We also proposed two approaches to train the model: (1) cross-lingual learning, replacing the activation function from source language to target language, and (2) multilingual learning. Our experiments on IARPA Babel datasets demonstrated that our approaches outperform the from-scratch training and traditional bottleneck feature based methods.
  arXiv  Detail & Related papers  (2022-05-28T04:02:59Z)
• Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0 [7.378368959253632]
  We show that a monolingual wav2vec-2.0 is a good few-shot ASR learner in several languages. A key finding of this work is that the adapted monolingual wav2vec-2.0 achieves similar performance as the topline multilingual XLSR model.
  arXiv  Detail & Related papers  (2021-10-07T15:29:22Z)
• Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification [73.5497360800395]
  We develop an end-to-end system that supports multiple languages. We exploit knowledge from a pre-trained multi-lingual natural language processing model.
  arXiv  Detail & Related papers  (2021-09-28T04:43:11Z)
• Are Multilingual Models Effective in Code-Switching? [57.78477547424949]
  We study the effectiveness of multilingual language models to understand their capability and adaptability to the mixed-language setting. Our findings suggest that pre-trained multilingual models do not necessarily guarantee high-quality representations on code-switching.
  arXiv  Detail & Related papers  (2021-03-24T16:20:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.