End-to-End Speech Processing Toolkit

include xbmu-amdo31 dataset

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

paper title: joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization

NeMo: a framework for generative AI

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models.

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

paper title: ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context

一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目，CPU上的实时率(RTF)小于0.1

[ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition

纯python实现机器学习算法,非套用sk-learn

paper: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

使用python进行语音识别

PyTorch re-implementation of Speech-Transformer

End-to-end ASR/LM implementation with PyTorch

Working online speech recognition based on RNN Transducer. ( Trained model release available in release )

机器学习实战项目

基于卷积神经网络的语音识别声学模型的研究