Gustavo Monti

Results 4 comments of Gustavo Monti

This is because TF changed your API due to version 1.x. You need to change: # self.h_pool = tf.concat(3, pooled_outputs) self.h_pool = tf.concat(pooled_outputs, 3) # flip params # losses =...

I opened a thread on dlib to retrain using this dataset, and I think this is not possible. https://github.com/davisking/dlib/issues/1407

Same here. First I needed to updated faster-whisper==0.10.0 and then receiving the same error above.