Saurabh Vyas's repositories
audioset_transfer
using Google's pretrained audioset model, to classify new audio categories
audio-classification
simple pytorch audio classification example
ctc_tensorflow_example
CTC + Tensorflow Example for ASR
dataset_creator
this small project, will help you to create datasets for audio related tasks, major code is taken from KT crawler git project
kaldi_scripts
a few useful kaldi scripts for my own use
tf_audio_sentiment
tensorflow code for binary sentimental classification ( happy and no happy ) for hindi data
ASR-System-for-Hindi-Language
The repository contains all the codes necessary for my project - Automatic Speech Recognition System in Hindi Language ( Project description is available at :- https://goo.gl/eQZkMP) : It containes the code for the following systems - 1) Monophone-HMM system built using HTK toolkit , 2)Monophone-HMM system built using Kaldi toolkit, 3)Triphone-HMM system built using Kaldi toolkit and 4)DNN-HMM system built using Kaldi toolkit
awesome-speech-recognition-speech-synthesis-papers
Automatic Speech Recognition, Speaker Verification, Speech Synthesis, Language Modeling
dataset_augment
code for augmenting dataset
dataset_builder
create dataset for asr
deep-voice-conversion
Deep neural networks for voice conversion (voice style transfer) in Tensorflow
deepspeech.pytorch
Speech Recognition using DeepSpeech2 and the CTC activation function. Edit
fast-wavenet
Speedy Wavenet generation using dynamic programming :zap:
feeny_voice
code for creating dataset for feeny , also useful for general purpose dataset creation
glossary_extractor
extract concepts from a book's glossary
ibm_speech
implementation of https://arxiv.org/pdf/1703.07754.pdf in tensorflow
nli_corpus_preprocess
preprocessing files for SNLI,SCITAIL AND MultiNLI datasets for training on custom setup
orange_vision_helper
This projects aims to solve a ton of real world problems. It will make use of open source CV, and speech tools to solve following problems :
tensor2tensor
A library for generalized sequence to sequence models
WER-in-python
This program calculates the word error rate of hypothesis in ASR and print the aligned result.