CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.
42 The CPU Memory Leak issue stems from the predict method of Keras, where there are inherent risks of memory leaks from global variables. Therefore, I switched to using the call method of TensorFlow. In the end, the issue has been resolved.
42 The CPU Memory Leak issue stems from the predict method of Keras, where there are inherent risks of memory leaks from global variables. Therefore, I switched to using the call method of TensorFlow. In the end, the issue has been resolved.