unsacmt

Multilingual Voice Understanding Model

An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.

“百聆”是一个基于LLaMA的语言对齐增强的英语/中文大语言模型，具有优越的英语/中文能力，在多语言和通用任务等多项测试中取得ChatGPT 90%的性能。BayLing is an English/Chinese LLM equipped with advanced language alignment, showing superior capability in English/Chinese generation, instruction following and multi-turn interaction.

A curated list of research papers and resources on code-switching

Text2Text Language Modeling Toolkit

Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion

Cross-Lingual Machine Reading Comprehension (EMNLP 2019)

Implementation of meta-transfer-learning for ASR and LM (ACL 2020)

SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 languages, generated using PaLM 2 and summarize-then-ask prompting.

A diffusion-based cross-lingual voice conversion model, as my bachelor's thesis