Vietnamese dataset

The 'Vietnamese dataset' is a benchmark used to evaluate the performance of inverse text normalization models, specifically in the context of streaming automatic speech recognition.

Papers using Vietnamese dataset (4)

How Far Do SSL Speech Models Listen for Tone? Temporal Focus of Tone Representation under Low-resource Transfer2025Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices2025Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization2025Efficient Utilization of Large Pre-Trained Models for Low Resource ASR2022