-
### Description
I trained Librispeech problem days ago and follow the notebook demo in [https://github.com/tensorflow/tensor2tensor/blob/master/docs/tutorials/asr_with_transformer.md](url)
when dec…
-
Hi all,
Thank you to the Magenta team for building this - it's truly amazing to see what a community like this can accomplish. Makes 2020 that much better 👍 Full disclosure - I'm coming at this fr…
-
I train with exactly the same setup (1GPU, transformer_big_single_gpu, batch_size=1500, en-cs dataset with 58M training sentences, checkpoints saved each hour) with T2T v1.2.9 and [v1.3.0](https://git…
-
### Description
trying to follow: https://github.com/tensorflow/tensor2tensor/blob/master/docs/cloud_tpu.md
getting "Failed to connect to the Tensorflow master" when running t2t_trainer
### Env…
-
i'm using
tensorflow-gpu 1.14.0,
tensor2tensor 1.10.0,
and magenta-gpu 1.0.1.
i was trying to run some examples with Score2Perf, magenta-gpu version 1.0.1.
(and never have used google cloud pl…
-
hi, when i am running TranslateEnzhWmt8k, when i set the vocabulary size to 8K, the generated chinese vocabulary is normal, but when set it to 32K, the file contains lots of lines like this:
it seems…
yuimo updated
6 years ago
-
I have trained a Transformer model for a speech recognition problem using the librispeech problem as the template. Training data includes librispeech but other datasets as well. The model appears t…
-
This problem was first reported at https://youtrack.jetbrains.com/oauth?state=%2Fissue%2FPY-38366
1 - I am running a unit test that is invoking the call(...) function of a TensorFlow model. I can s…
-
Hello , I use T2T for translation task, it's version is 1.5.5.
The setting I use as follows:
PROBLEM=translate_enzh_wmt32k
MODEL=transformer
HPARAMS=transformer_base_single_gpu
I used t2t-tra…
-
### Description
There are some problems when using the BERT class from trax/models/research/bert.py. The method new_weights(self, input_signature) in PretrainedBERT class is using `super().new_weig…