ShiLiang Zhang

This is now the official location of the Kaldi project.

No description provided.

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

Ongoing research training transformer language models at scale, including: BERT & GPT-2

A Fundamental End-to-End Speech Recognition Toolkit

Awesome speech/audio LLMs, representation learning, and codec models

:arrow_double_down: Dumb downloader that scrapes the web

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Awesome-LLM: a curated list of Large Language Model

An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.

An experimental open-source attempt to make GPT-4 fully autonomous.

🔊 Text-prompted Generative Audio Model

Code and documentation to train Stanford's Alpaca models, and generate the data.

A TensorFlow implementation of Baidu's DeepSpeech architecture

End-to-End Speech Processing Toolkit

Master the command line, in one page

The PyTorch-based audio source separation toolkit for researchers

Automatic Speech Recognition, Speaker Verification, Speech Synthesis, Language Modeling

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

TensorFlow code and pre-trained models for BERT

A PyTorch implementation of Google AI's BERT model provided with Google's pre-trained models, examples and utilities.

Neural machine translation and sequence learning using TensorFlow

Open Source Neural Machine Translation in PyTorch

Models and examples built with TensorFlow

Computation using data flow graphs for scalable machine learning