yygle

OpenPhonemizer

An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GPL phonemizer.

diffusion_tutorial

diffusion generative model

Emu

Emu Series: Generative Multimodal Models from BAAI

Auto_Tuning_Zeroshot_TTS_and_VC

Official implementation of "Automatic Tuning of Loss Trade-offs without Hyper-parameter Search in End-to-End Zero-Shot Speech Synthesis", Interspeech 2023

Chinese-Vicuna

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

FT-w2v2-ser

Official implementation for the paper Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition

TIM-Net_SER

[ICASSP 2023] Official Tensorflow implementation of "Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition".

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

audiolm-pytorch

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

vall-e

An unofficial PyTorch implementation of the audio LM VALL-E

LIGHT-SERNET

Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition

icefall

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Squeezeformer

[NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition

rotary-embedding-torch

Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

FLASH-pytorch

Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"

RepVGG

RepVGG: Making VGG-style ConvNets Great Again

performer-attention-tensorflow

An implementation of Performer attention with TensorFlow

Flat-Lattice-Transformer

code for ACL 2020 paper: FLAT: Chinese NER Using Flat-Lattice Transformer

cuBERT

Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL

AttentionPathExplainer

A tool to help understand how GNN/BERT works by attention

Ai-Learn

人工智能学习路线图，整理近200个实战案例与项目，免费提供配套教材，零基础入门，就业实战！包括：Python，数学，机器学习，数据分析，深度学习，计算机视觉，自然语言处理，PyTorch tensorflow machine-learning,deep-learning data-analysis data-mining mathematics data-science artificial-intelligence python tensorflow tensorflow2 caffe keras pytorch algorithm numpy pandas matplotlib seaborn nlp cv等热门领域

pke

Python Keyphrase Extraction module

Synonyms

:herb: 中文近义词：聊天机器人，智能问答工具包

tensorflow

An Open Source Machine Learning Framework for Everyone

ChineseNLPCorpus

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

text-classification-cnn-rnn

CNN-RNN中文文本分类，基于TensorFlow

BERT-for-Sequence-Labeling-and-Text-Classification

This is the template code to use BERT for sequence lableing and text classification, in order to facilitate BERT for more tasks. Currently, the template code has included conll-2003 named entity identification, Snips Slot Filling and Intent Prediction.

scenario_nlp

基于意图识别和命名实体识别的多轮对话场景设计