Compact N-gram Language Models for Armenian
Davit Karamyan, Tigran Karamyan · Mathematical Problems of Computer Science · 2022
Applications such as speech recognition and machine translation use language models to select the most likely translation among many hypotheses. For on-device applications, inference time and model size are just as important as performance. In this work, we explored the fastest family of language models: the N-gram models for the Armenian language. In addition, we researched the impact of pruning and quantization methods on model size reduction. Finally, we used Bye Pair Encoding to build a subword language model. As a result, we obtained a compact (100 MB) subword language model trained on massive Armenian corpora.