NeFut Logo NeFut
Admin Login

[CS.AI] Workload-Driven Optimization for Real-Time Subtitle Translation

Published at: 2026-07-19 22:00 Last updated: 2026-07-22 01:02
#AI #Machine Learning #Open Source

Abstract

This report investigates on-device English-to-Traditional-Chinese subtitle translation for Taiwan under constraints of short inputs, short outputs, batch-size-one inference, low latency, and privacy. These conditions limit the effectiveness of optimizations designed for long-context or high-throughput language model serving.

Starting from LMT-60-0.6B, preliminary profiling suggests that vocabulary projection becomes a more significant decode-time cost after GGUF quantization reduces the relative cost of Transformer blocks. We replace the original 151k-token vocabulary with a 64k-token subtitle-domain tokenizer, migrate the embedding space, and adapt the model through embedding calibration followed by full supervised fine-tuning.

On the OpenSubtitles2024 test set, LocalSubs achieves a 59.2% tie-excluded win rate against Google Translate under GPT-4o pairwise judging. Performance is strongest on short cues and declines as cue length increases.

In a separate preliminary Apple M2 Metal profiling run, LocalSubs shows a 1.63x speedup over a 151k-vocabulary baseline. The code is available on GitHub.

Blogger's Review: This paper effectively demonstrates how optimizing vocabulary and fine-tuning models can enhance real-time translation performance in specific application scenarios. Especially with low-latency and privacy requirements, exploring new model architectures and optimization strategies is crucial for further research and practice.

Original Source: https://arxiv.org/abs/2607.09957

[h] Back to Home