PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASSP 2020)
-
Updated
Feb 27, 2022 - Python
#
transformer-transducer
Here are 4 public repositories matching this topic...
Korean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)
end-to-end pytorch transformer speech-recognition asr korean-speech-recognition ksponspeech transformer-transducer korean-asr transforme-joint-ctc
-
Updated
Feb 19, 2021 - Python
Deep learning-based subtitle generation model that processes audio datasets to generate accurate text transcriptions. Includes audio feature extraction, encoder-decoder architecture, training pipelines, and evaluation metrics for subtitle alignment.
deep-neural-networks tensorflow dnn recurrent-neural-networks lstm gru rnn speech-to-text sequence-to-sequence rnn-tensorflow gated-recurrent-units rnnt online-speech-recognition transformer-transducer
-
Updated
Feb 20, 2025
Improve this page
Add a description, image, and links to the transformer-transducer topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the transformer-transducer topic, visit your repo's landing page and select "manage topics."