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

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

A curated list of pretrained sentence and word embedding models

Text2Text Language Modeling Toolkit

A multilingual phoneme recognizer capable of generalizing zero-shot to unseen phoneme inventories.

Multilingual Voice Understanding Model

ISCC - Semantic Code Text

Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment

Discovering Universal Geometry in Embeddings with ICA

Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity

[KDD 2024] Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning

Code for InfoCTM: A Mutual Information Maximization Perspective of Cross-lingual Topic Modeling (AAAI2023)

Official code and data release for Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning, accepted by findings of EACL 2024.

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

“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.

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.

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

Improving Zero-Shot Cross-Lingual Hate Speech Detection with Pseudo-Label Fine-Tuning of Transformer Language Models

Codebase of Cross-Lingual Neural Databases

This is the repository for the newly created Czech Subjectivity Dataset (Subj-CS) and our paper: