Stars
Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
Python interface to the WebRTC Voice Activity Detector
nangongmu / deep-speaker
Forked from philipperemy/deep-speakerDeep Speaker: an End-to-End Neural Speaker Embedding System https://arxiv.org/pdf/1705.02304.pdf
This repo contains code for speech vs music vs noise classification
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
You can find the speech algorithms you want here
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
python codes to extract MFCC and FBANK speech features for Kaldi
A Convolutional Neural Network based Voice Activity Detector for Smartphones
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…
Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196
100+ Chinese Word Vectors 上百种预训练中文词向量
Speech Recognition using DeepSpeech2.
Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.
A PyTorch Implementation of End-to-End Models for Speech-to-Text
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
中文语音识别; Mandarin Automatic Speech Recognition;
Dockerfile for compiling Kaldi for Android.
基于kaldi的ios本地语音识别（本地实时流）Kaldi-based ios native speech recognition (local real-time streaming)
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding a…
kaldi-asr/kaldi is the official location of the Kaldi project.
Code samples used on cloud.google.com
Facebook AI Research's Automatic Speech Recognition Toolkit