-
Hey T2T team,
Great repo. I've been trying to investigate how to add a penalty for repeated words which occur sometimes in translations. For example "He went to get milk milk milk".
Inspired by…
-
### Description
I get this error when I import trax. Can someone help me to fix it?
### Environment information
```
OS: macOS Big Sur
$ pip freeze | grep trax
trax==1.3.7
$ pip freeze |…
-
There are a few improvements that could be made to the transformer implementation:
1. We have not confirmed that it gets competitive performance with the original implementation, nor created a reci…
-
Hello everyone
I have the pip installation of magenta-2.1.2 and other models such as musicVAE work.
But I cannot have GANSynth working unfortunately ..
I read this issue was opened and solved, …
-
Does this solve question generation problem?
-
Hello there,
First of all, thank you for releasing this amazing product. As a TensorFlow user, I was wondering if you plan to allow to load seq2seq model trained using TensorFlow. Do you think that…
-
Hello,
I am having multiple issues with score2perf that seem to have to do with the dependencies in setup.py, and tensorflow 2.0 (including removal of tf.contrib). When I enforce a lower version fo…
-
Hey,
For Machine Translation (Transformer model) Default of 16k steps is what I'm using for learning_rate_warmup_steps irrespective of the batch size.
Are there any recommendation or best practic…
-
#### What is your question?
I have trained the newly added Conformer model on MuST-C En-Es and I noticed that sometimes it starts to repeat the same words or part of sentence, here is an example:
`P…
-
As above, i want to add a new embedding for input embedding.
The older = word embedding + position embedding.
The new = word embedding + position embedding + my own embedding
where are the codes i …