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

Multilingual Voice Understanding Model

A curated list of pretrained sentence and word embedding models

Text2Text Language Modeling Toolkit

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

“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.

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

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

Cross-Lingual Machine Reading Comprehension (EMNLP 2019)

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

MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models

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

Code and data for EMNLP 2018 paper "Cross-lingual Lexical Sememe Prediction"

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

Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems (AAAI-2020)

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

Zero-shot Cross-lingual Task-Oriented Dialogue Systems (EMNLP 2019)

Unsupervised Sentiment Analysis for Code-mixed Data

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

Cross-lingual version of WEAT