Cantonese, the second most prevalent Chinese dialect after Mandarin, has been relatively overlooked in machine translation (MT) due to a scarcity of bilingual resources. In this paper, we propose to leverage Mandarin, a high-resource language, as a pivot language for translating between Cantonese and English. Our method utilizes transfer learning from pre-trained Bidirectional and Auto-Regressive Transformer (BART) models to initialize auxiliary source-pivot and pivot-target MT models. The parameters of the trained auxiliary models are then used to initialize the source-target model. Based on our experiments, our proposed method outperforms several baseline initialization strategies, naive pivot translation, and two commercial translation systems in both translation directions.