search

TensorSpeech / TensorFlowASR

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
https://huylenguyen.com/asr
Apache License 2.0
929 stars 243 forks source link

Real-time inference example #211

Open elaith9 opened 3 years ago

elaith9 commented 3 years ago

Hello! I'm wondering if is possible to use those models in real-time inference scenario like microphone stream. In other words, will models work good on smaller chunks of audio like 250ms instead on whole sentences like those used for training. And if you have some example would you be able to provide it. Thanks, and great work!

nglehuy commented 3 years ago

@elaith9 Ideally the rnn_transducer can work on the small chunk of audio, but we need to test more :smile: