Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913759545524224 |
|---|---|
| author | Meng, Yangyang Li, Jinpeng Lin, Guodong Pu, Yu Wang, Guanbo Du, Hu Shao, Zhiming Huang, Yukai Li, Ke Zhang, Wei-Qiang |
| author_facet | Meng, Yangyang Li, Jinpeng Lin, Guodong Pu, Yu Wang, Guanbo Du, Hu Shao, Zhiming Huang, Yukai Li, Ke Zhang, Wei-Qiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20212 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages Meng, Yangyang Li, Jinpeng Lin, Guodong Pu, Yu Wang, Guanbo Du, Hu Shao, Zhiming Huang, Yukai Li, Ke Zhang, Wei-Qiang Computation and Language Audio and Speech Processing 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. |
| title | Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2503.20212 |