Instead of librosa.stft, what can i use in audio.py?

Kyubyong / dc_tts

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

Apache License 2.0

1.16k stars 370 forks source link

Instead of librosa.stft, what can i use in audio.py? #86

Open berkaycinci opened 3 years ago

berkaycinci commented 3 years ago

Guys, i am trying to implement this project on a embedded device. Because of some limitations on the embedded device, i can not install librosa. That's why, i am trying to replace stft and istft methods which are utilized inside audio.py. Do you have any suggestions? @Kyubyong

dmmagdal commented 3 years ago

Tensorflow has the tf.signal.stft function in Tensorflow 1.15 and Tensorflow 2.X. Have you tried those?