Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Multilingual Voice Understanding Model

A curated list of pretrained sentence and word embedding models

A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech

PyTorch Implementation of TCSinger(EMNLP 2024): Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control

“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.

Text2Text Language Modeling Toolkit

PyTorch Implementation of TCSinger 2(ACL 2025): Customizable Multilingual Zero-shot Singing Voice Synthesis

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

AAAI-20 paper: Cross-Lingual Natural Language Generation via Pre-Training

Cross-Lingual Machine Reading Comprehension (EMNLP 2019)

This repo is text to speech with learnable audio encoder without alignment with transcript reference

This repo contains the code for the paper Neural Factor Graph Models for Cross-lingual Morphological Tagging.

Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework

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 Multi-subject High School Examinations Dataset for Cross-lingual and Multilingual Question Answering

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

Deep-learning system proposed by HFL for SemEval-2022 Task 8: Multilingual News Similarity

EMNLP 2022: ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization