Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages
Authors:
Preprint
Abstract
This report introduces Dolphin, a large-scale multilingual automatic speech recognition (ASR) model that extends the Whisper architecture to support a wider range of languages. Our approach integrates in-house proprietary and open-source datasets to refine and optimize Dolphin's performance. The model is specifically designed to achieve notable recognition accuracy for 40 Eastern languages across East Asia, South Asia, Southeast Asia, and the Middle East, while also supporting 22 Chinese dialects. Experimental evaluations show that Dolphin significantly outperforms current state-of-the-art open-source models across various languages. To promote reproducibility and community-driven innovation, we are making our trained models and inference source code publicly available.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement2025
- OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer2024
- Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition2022
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech ProcessingIEEE Journal of Selected Topics in Signal Processing, 2022
- Improving Automatic Speech Recognition Performance for Low-Resource Languages With Self-Supervised ModelsIEEE Journal of Selected Topics in Signal Processing, 2022
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden UnitsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- Hybrid CTC/Attention Architecture for End-to-End Speech RecognitionIEEE Journal of Selected Topics in Signal Processing, 2017
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Tags for Identifying Languages2006