🔊 Text-Prompted Generative Audio Model

这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时)， 所以识别效果也很好，可以媲美许多商用的ASR软件。

Foundation Architecture for (M)LLMs

An Open-Source Package for Neural Relation Extraction (NRE)

An Open-Source Package for Knowledge Embedding (KE)

CAT is more than a CRF-based ASR toolkit: it provides a complete workflow for data-efficient end-to-end ASR, supporting CTC, CTC-CRF, RNN-T, and language-model training and inference.

Lingvo

Share and collaborate by syncing with any Git repository instantly. Linux, macOS, and Windows

DeepMind's Tacotron-2 Tensorflow implementation

Check out the new game server:

A fast parallel implementation of RNN Transducer.

Praat in Python, the Pythonic way

Fast parallel CTC.

TensorFlow code and pre-trained models for BERT

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Audio spectrogram in canvas.

Fork of https://code.google.com/archive/p/ipv6-hosts/, focusing on automation

Python functions for reading kaldi data formats. Useful for rapid prototyping with python.

kaldi-asr/kaldi is the official location of the Kaldi project.

scikit-learn: machine learning in Python