Pith. sign in

REVIEW 3 cited by

Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.20212 v1 pith:WGVJ2HYW submitted 2025-03-26 cs.CL eess.AS

Yangyang Meng , Jinpeng Li , Guodong Lin , Yu Pu , Guanbo Wang , Hu Du , Zhiming Shao , Yukai Huang
show 2 more authors
Ke Li Wei-Qiang Zhang
This is my paper
classification cs.CLeess.AS
keywords dolphinlanguagesasiamodelrecognitionacrossautomaticeast
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models

    cs.CL 2026-04 conditional novelty 6.0 of 10

    Synthetic data for low-resource spoken language models creates a Stability-Expressivity Gap that DGSA and TDSC self-alignment close, enabling SOTA Thai TTS and first Lao zero-shot voice cloning.

  2. WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation

    cs.SD 2025-09 conditional novelty 6.0 of 10

    The authors built and released the largest open-source Cantonese speech corpus (21,800 hours, 10 domains, rich metadata), and show that models trained on it match or beat existing speech recognition and synthesis systems.

  3. ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition

    cs.CL 2025-07 conditional novelty 4.0 of 10

    A three-stage iterative LoRA training recipe (Focus, Feed Back, Fix) is applied to Whisper-large-v3 and Qwen2-Audio, reporting WER reductions on a multilingual ASR benchmark, with the gains attributed to the iterative...

Pith tools