-
I installed all the required libraries. When I run ./setup, it gets stuck after some time and remain stuck for at least 8 hours.
Here is the output:
data/model.t7: OK
----------------Installing…
-
I used default dl4mt_nist_zh2en.yaml to train DL4MT model on 1.25M NIST zh-en corpus and I found the code occupies ~10G gpu memory, which is much higher than my in-house implementation. I checked DL4M…
-
Hello,
I'm attempting to reproduce the results reported in your paper, particularly one of the entries for the PBM 2.1 dataset.
The issue that I'm having right now is that the embedding file is…
-
Hi there,
Is it possible to add a weight vector while training the encoder-decoder model for the purpose of adding contextual data? Or even supporting multiple input to get an output? Basically, th…
-
I'm not sure if it's appropriate to create an issue for this, but I wasn't really sure where the best place was to ask. Are there any current known issues or limitations with using this branch?
I'm p…
-
OpenNMT Lua version supports extra word features concatenated with token with "｜" delimiter and the decoder can also make predictions of word features.
I'm wondering if Tensorflow version has this fu…
-
https://arxiv.org/pdf/1704.04368.pdf
-
we now add `tiny` into our ci pipeline, which is about 70mb large.
it will be great if there's a small enough working model for ci test, similar to those `hf-internal-testing` models
-
Tried to convert a transformer model from OpenNMT-py which uses "mlp" for it's embeddings but MLP hasn't been incorporated into conversion, so I assume it's not supported in CTranslate2.
```python
…
-
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…