Skip to content

v1.0.0-SpeechRecognitionRNN

Latest
Compare
Choose a tag to compare
@Andersonjesusvital Andersonjesusvital released this 18 Jan 21:42
· 3 commits to main since this release

Version 1.0.0 of "Speech-Recognition-RNN" repository offers a deep learning-based subtitle generation model for processing audio datasets to produce accurate text transcriptions. It includes features like audio feature extraction, an encoder-decoder architecture, training pipelines, and evaluation metrics for assessing subtitle alignment.