Dolphin-CN-Dialect: Where Chinese Dialects Matter

TL;DR

Dolphin-CN-Dialect is a streaming-capable ASR model optimized for Chinese dialects, featuring improved data handling, tokenization, and sampling strategies, achieving high accuracy and efficiency in dialect recognition.

Contribution

The paper introduces a novel temperature-based sampling strategy and a redesigned tokenizer tailored for Chinese dialects, enhancing dialect recognition and model performance.

Findings

Significant gains in dialect recognition accuracy.

Reduced CER compared to previous models.

Achieves competitive performance with state-of-the-art ASR models.

Abstract

We present Dolphin-CN-Dialect, a streaming-capable ASR model with a focus on Chinese and dialect-rich scenarios. Compared to the previous version, Dolphin-CN-Dialect introduces substantial improvements in data processing, tokenization, training stability, and data sampling strategies. To address the challenges of highly imbalanced dialect data, we propose a temperature-based sampling strategy that effectively balances standard Mandarin and low-resource dialects, leading to significant gains in dialect recognition performance. In addition, we redesign the tokenizer to better align with linguistic characteristics, adopting character-level modeling for Chinese and subword modeling for English, while introducing extensible dialect tokens. Experimental results show that Dolphin-CN-Dialect achieves improvement in dialect recognition accuracy and CER reduction compared to Dolphin. Furthermore, Dolphin-CN-Dialect reaches competitive performance with recent SOTA open-source ASR models, while maintaining a significantly smaller model size. Dolphin-CN-Dialect supports both streaming and non-streaming inference, enabling a practical balance between latency and accuracy. It also provides flexible customization through hotword support and efficient deployment optimized for specialized hardware. These improvements make Dolphin-CN-Dialect a strong and practical solution for real-world multi-dialect ASR applications.