🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目，还可能是首个支持脑机交互的开源智能音箱项目。

Lingvo

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

DELTA is a deep learning based natural language and speech processing platform.

A Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

The official repository of the Eesen project

SincNet is a neural architecture for efficiently processing raw audio samples.

A Python wrapper for Kaldi

Open STT

A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.

Sequence-to-Sequence Framework in PyTorch

Silero Models: pre-trained STT models and benchmarks made embarrassingly simple

On-device streaming speech-to-text engine powered by deep learning

an open-source implementation of sequence-to-sequence based speech processing engine

Open tools and data for cloudless automatic speech recognition

End-to-end ASR/LM implementation with PyTorch

End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)

语音识别理论，论文和PPT

Dockerfile for kaldi-gstreamer-server.

A Keras CTC implementation of Baidu's DeepSpeech for model experimentation

Kaldi-based Korean ASR (한국어 음성인식) open-source project

Offline speech recognition for Android with Vosk library.

The S3PRL speech toolkit: self-supervised pre-training and representation learning of Mockingjay, TERA, A-ALBERT, APC, and more to come. With easy-to-use standard downstream evaluation scripts including phone classification, speaker recognition, and ASR. (All in Pytorch!)

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

Chinese text normalization for speech processing

WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries

Python module for evaluating ASR hypotheses (e.g. word error rate, word recognition rate).

使用FreeSWITCH接受用户手机呼叫，通过UniMRCP Server集成讯飞开放平台（xfyun）插件将用户语音进行语音识别（ASR），并根据自定义业务逻辑调用语音合成（TTS），构建简单的端到端语音呼叫中心。