ishine's Projects
Simple Kaldi model server for chain (nnet3) models in online recognition mode directly from a local microphone
Extended speech recognition neural network based on Kaldi for reproducible research
Neural network phone duration model on top of the Kaldi speech recognition framework
Implementation of different noise embeddings for noise aware training of Kaldi acoustic models.
Kaldi model converter to ONNX
Server framework for Kaldi ASR Toolkit
This repository creates speaker diarization recipes to be used within the egs folder of kaldi.
Convert kaldi nnet3 models into Tensorflow Lite models. Currently aimed at converting kaldi's x-vector models and diarization pipelines to tensorflow models.
a few useful kaldi scripts for my own use
cmake based kaldi + vosk + microphone speech recognition example
Kaldi based speaker verification
Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API
KALDI Spoken term detection wrapper
Python server for communicating with Kaldi from the browser using WebRTC
这是一个Kalman Filter的程序,内含状态量为标量和二维矢量的C程序实现
UnOfficial repository for the paper Karatuner
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.
Knowledge Graph,Question Answering System,基于知识图谱和向量检索的医疗诊断问答系统
Deep Learning Chinese Word Segment
Knowledge Graph Embedding Based Question Answering
Facenet implementation by Keras2