Blitzing Fast CTC Beam Search Decoder

VietASR - Vietnamese Automatic Speech Recognition

This repo builds an end-to-end deep learning application that supports speech recognition system. It's simple to use and understand :smile:

Adnabod lleferydd Cymraeg i'r Gymraeg gyda HuggingFace // Speech Recognition for Welsh with HuggingFace

Real-Time ASR with CNN-BiLSTM: End-to-End Live Streaming Using PyTorch Lightning⚡

Automatic Speech Recognition using Conformer with Speech Sentiment Analysis & Text Summarizer

Spoken word recognition using CTC LSTMs for SWR2 Tübingen

An end-to-end speech recognition engine similar to DeepSpeech2

Custom tensorflow op for ctc beam search that keeps track of best alignment for each beam

Automatic speech recognition model for the Spoken Word Recognition seminar (SWR2) Tübingen

Implementation of Deep Speech 2 paper with BiGRU and BiLSTM using LibriSpeech Dataset

Flask web application recognizes a single word or number from an image based on deep learning word and digit recognition that combines a hybrid inference pipeline with the use of TensorFlow, a CNN + BiLSTM (CRNN) architecture, and CTC decoding.