realtime-voice-conversion based on last year's work

This is based on the work I did in (July - October)ish 2019 to get real
time voice conversion working. I've removed it from the `voder` library
and made it into an isolable program. I'll work on extending the
capabilities.

cycle_gan/utils.py

@@ -0,0 +1,17 @@
+import tensorflow as tf
+import os
+import random
+import numpy as np
+
+def l1_loss(y, y_hat):
+
+    return tf.reduce_mean(tf.abs(y - y_hat))
+
+def l2_loss(y, y_hat):
+
+    return tf.reduce_mean(tf.square(y - y_hat))
+
+def cross_entropy_loss(logits, labels):
+    return tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits = logits, labels = labels))
+
+