traxplease use this room: https://gitter.im/trax-ml/community
weight_0 not found in checkpointerror that is probably due to a version mismatch
Hi all, I am experimenting with a speech to text model trained using tensor2tensor (not by me). I only have access to saved_model format generated using t2t-export and the vocab for decoding.
Is it possible to change the decoding params of the exported model?
Is there some way to see all the beam outputs instead of the top scoring one?
Any help/suggestions are appreciated. Thank you.
When I train my transformer using t2t-trainer, I see the targets/accuracy go up to around 65% on tensorboard. But then when I try:
t2t-decoder --data_dir=$DATA_DIR --problem=$PROBLEM --model=$MODEL --hparams_set=$HPARAMS --output_dir=$TRAIN_DIR --t2t_usr_dir='.'
It looks like none of the OUTPUTs matches the corresponding TARGETs. Am I missing something obvious?
AttributeError: 'HParams' object has no attribute 'audio_compression'
for i in xrange(self._model_hparams.audio_compression):