集成了Tensorflow 2版本的端到端语音识别模型，并且RTF(实时率)在0.1左右/Mandarin State-of-the-art Automatic Speech Recognition in Tensorflow 2

Dual-Path Style Learning for End-to-End Noise-Robust Automatic Speech Recognition (DPSL-ASR).

Speech Algorithms Collections

Official open source implementation of the paper "Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation"

An audio/acoustic activity detection and audio segmentation tool

Git的奇技淫巧

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

Chinese text normalization for speech processing

A data annotation pipeline to generate high-quality, large-scale speech datasets with machine pre-labeling and fully manual auditing.

A library for speech data augmentation in time-domain

End-to-End Speech Processing Toolkit

这个工程的目的是从视频中获取语音识别的训练数据，用于训练字幕自动生成