Multilingual Distilwhisper: Efficient Distillation Of Multi-task Speech Models Via Language-specific Experts

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 i

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keyferraz2023multilingual

Related papers

• Dq-whisper: Joint Distillation And Quantization For Efficient Multilingual Speech Recognition (2023)4.52
• Whisper-lm: Improving ASR Models With Language Models For Low-resource Languages (2025)3.29
• M2r-whisper: Multi-stage And Multi-scale Retrieval Augmentation For Enhancing Whisper (2024)6.77
• Simul-whisper: Attention-guided Streaming Whisper With Truncation Detection (2024)6.34
• Adapting Whisper For Code-switching Through Encoding Refining And Language-aware Decoding (2024)0.00
• Cross-lingual Transfer Learning For Speech Translation (2024)6.34
• Sparsely Shared Lora On Whisper For Child Speech Recognition (2023)9.59
• On The Transferability Of Whisper-based Representations For "in-the-wild" Cross-task Downstream Speech Applications (2023)0.00