kakashidan

ddia

《Designing Data-Intensive Application》DDIA中文翻译

kaldi

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

fancyss_history_package

科学上网插件的离线安装包储存在这里

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

ECDICT

Free English to Chinese Dictionary Database

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

space-vim

:four_leaf_clover: Lean & mean spacemacs-ish Vim distribution

OFA

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

cnnimageretrieval-pytorch

CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

Deep_Metric

Deep Metric Learning

Speech-enhancement

Deep learning for audio denoising

chinese_text_normalization

Chinese text normalization for speech processing

word-discovery

速度更快、效果更好的中文新词发现

research-ms-loss

MS-Loss: Multi-Similarity Loss for Deep Metric Learning

g2pm

A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset

StreamingTransformer

multigrain

Code for "MultiGrain: a unified image embedding for classes and instances"

pychain

PyTorch implementation of LF-MMI for End-to-end ASR

cn-text-normalizer

A python module that convert chinese written string to read string. 一个python包：将中文书面字符串转换为口语字符串。

KeSpeech

The repo provides information about KeSpeech dataset.

pkwrap

A pytorch wrapper for LF-MMI training and parallel training in Kaldi

speech-to-text

mixlingual speech recognition system; hybrid (GMM+NNet) model; Kaldi + Keras

multi-task-kaldi

An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 training.

goparrot

Goodness of Pronunciation (GOP) for oral reading assessment.

multistream-cnn

Multistream CNN for Robust Acoustic Modeling

Text_Normalization

A text normalization framework using GBM and human-generated features