GRU's repositories
tflite-models-audioset-yamnet
A TFLite-compatible fork of YAMNet from tensorflow/models
open_stt
Open STT
avsr-tf1
Audio-Visual Speech Recognition using Sequence to Sequence Models
SemanticMask
The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"
lac
百度NLP:分词,词性标注,命名实体识别
voxceleb_trainer
In defence of metric learning for speaker recognition
Lipreading-DenseNet3D
DenseNet3D Model In "LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild", https://arxiv.org/abs/1810.06990
Chatbot_CN
基于金融-司法领域(兼有闲聊性质)的聊天机器人,其中的主要模块有信息抽取、NLU、NLG、知识图谱等,并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口
amr-eager
Parser for Abstract Meaning Representation
PunctuationPrediction-BERT
Use bert to predict punctuation on IWSLT2012 and The People's Daily 2014
SuperpoweredLatency
This application measures round-trip audio latency on an iOS or Android device. Low round-trip audio latency is a strong indicator of how well any mobile device is optimized for professional audio. Lower latency confers significant benefits to users of all sorts of apps like games, augmented hearing apps, VOIP and other interactive apps. Read more: http://superpowered.com/latency
AutoSpeech2020
1st place solution to Automated Machine Learning https://www.automl.ai/competitions/2
XLM
PyTorch original implementation of Cross-lingual Language Model Pretraining.
coach
Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (ACL-2020)
abseil-cpp
Abseil Common Libraries (C++)
uda
Unsupervised Data Augmentation (UDA)
stopwords-1
中文常用停用词表(哈工大停用词表、百度停用词表等)
bss
工学博覧会 : 音源分離チーム
deep-disfluency-detector
Disfluency Detection using Auto-Correlational Neural Networks
fast_align
Simple, fast unsupervised word aligner
pykaldi
A Python wrapper for Kaldi
chinese_text_normalization
Chinese text normalization for speech processing
acoustic_punctuation
NMT based punctuation prediction system using lexical and acoustic features .
nisaba
A tool for multi-modal annotation
DNN-for-speech-enhancement
DNN-for-speech-enhancement