mowayao's repositories
chinese_text_normalization
Chinese text normalization for speech processing
antialiased-cnns
Antialiasing cnns to improve stability and accuracy. In ICML 2019.
argus-freesound
Kaggle | 6th place solution [public LB] for Freesound Audio Tagging 2019
bert_distill
BERT distillation(基于BERT的蒸馏实验 )
Books
My book list
cuBERT
Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
fast-autoaugment
Official Implementation of 'Fast AutoAugment' in PyTorch.
ge2e-speaker-verification
Pytorch implement of "Generalized End-to-End Loss for Speaker Verification"
MachineLearningDOC
图像、人脸、OCR、语音相关算法整理
mmdetection
Open MMLab Detection Toolbox and Benchmark
numpy-ml
Machine learning, in numpy
open-speech-corpora
A list of accessible speech corpora for ASR.
openbilibili
哔哩哔哩后台源码
pycorrector
pycorrector is a toolkit for text error correction. It was developed to facilitate the designing, comparing, and sharing of deep text error correction models.
pytorch-onnx-tvm
PyTorch -> ONNX -> TVM for autotuning
pytorchic-bert
Pytorch Implementation of Google BERT
Speech-Transformer
A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.
StudyBook
Study E-Book(ComputerVision DeepLearning MachineLearning Math NLP Python ReinforcementLearning)
torchvggish
PyTorch conversion of Google's VGGish model used for extracting audio features for AudioSet. (https://github.com/tensorflow/models/tree/master/research/audioset)
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.