Hello,
just a topic to discuss the use of Rectifier Adam (RAdam) instead of Adam in DeepSpeech.
If I trust this link using Radam might improve results.
Did this method will be implemented or is it not in the current reflexion ?
Hello,
just a topic to discuss the use of Rectifier Adam (RAdam) instead of Adam in DeepSpeech.
If I trust this link using Radam might improve results.
Did this method will be implemented or is it not in the current reflexion ?
As far as I can tell, it’s not on our radar.
Is an RAdam implementation in TensorFlow?
It might be interesting to test it, don’t know if there will be improvement