ICTNLP

awesome-transformer

A collection of transformer's guides, implementations and variants.

BayLing

“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.

DASpeech

Code for NeurIPS 2023 paper "DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation".

DialoFlow

Code for ACL 2021 main conference paper "Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances".

DSTC8-AVSD

We rank the 1st in DSTC8 Audio-Visual Scene-Aware Dialog competition. This is the source code for our IEEE/ACM TASLP (AAAI2020-DSTC8-AVSD) paper "Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog".

LLaMA-Omni

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

NAST-S2x

A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.

OR-NMT

Source Code for ACL2019 paper <Bridging the Gap between Training and Inference for Neural Machine Translation>

StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

TruthX

Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"

ictnlp/LLaMA-Omni

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

ictnlp/BayLing

“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.

ictnlp/Auto-RAG

This is the official repository for Auto-RAG.

ictnlp/TruthX

Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"

ictnlp/NAST-S2x

A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.

ictnlp/DASpeech

Code for NeurIPS 2023 paper "DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation".

ictnlp/DiSeg

Source code for ACL 2023 paper "End-to-End Simultaneous Speech Translation with Differentiable Segmentation"

ictnlp/ComSpeech

Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".

ictnlp/HMT

Source code for ICLR 2023 spotlight paper "Hidden Markov Transformer for Simultaneous Machine Translation"

ictnlp/CRESS

Code for ACL 2023 main conference paper "Understanding and Bridging the Modality Gap for Speech Translation".

ictnlp/TACS

Source code for Truth-Aware Context Selection: Mitigating the Hallucinations of Large Language Models Being Misled by Untruthful Contexts

ictnlp/CMOT

Code for ACL 2023 main conference paper "CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation"

ictnlp/SiLLM

SiLLM is a Simultaneous Machine Translation (SiMT) Framework. It utilizes a Large Language model as the translation model and employs a traditional SiMT model for policy-decision to achieve SiMT through collaboration.

ictnlp/BT4ST

Code for ACL 2023 main conference paper "Back Translation for Speech-to-text Translation Without Transcripts".

ictnlp/Convex-Learning

Code for NeurIPS 2023 paper "Beyond MLE: Convex Learning for Text Generation"

ictnlp/PCFG-NAT

Code for NeurIPS 2023 paper "Non-autoregressive Machine Translation with Probabilistic Context-free Grammar".

ictnlp/MonoAttn-Transducer

Code Implementation for Paper "Learning Monotonic Attention in Transducer for Streaming Generation"

ictnlp/CTC-S2UT

Code for ACL 2024 findings paper "CTC-based Non-autoregressive Textless Speech-to-Speech Translation"

ictnlp/SU4MT

Code for EMNLP 2023 paper "Enhancing Neural Machine Translation with Semantic Units"

ictnlp/Multiscale-Contextualization

ACL2024 Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation

ictnlp/DST

DST is a Decoder-only simultaneous machine translation model, which can conduct policy decision and translation concurrently

ictnlp/SAMMT

Code for EMNLP 2023 paper "Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation"

ictnlp/SemLing-MNMT

Code for ACL 2024 paper "Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features".

ictnlp/ComSpeech-Site

ictnlp/MoCE

code for paper: "MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation"

ictnlp/StreamSpeech-site

ictnlp/TruthX-site

ictnlp/LengthBiasDNMT

ictnlp/TA-AT

Official code for AAAI24 paper "TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling"