-
I want to train t5 from scratch, and use my own vocabulary.
the model i can load like this:
config = T5Config.from_json_file(config_file)
model = T5ForConditionalGeneration(config)
the vocabul…
-
[/home/nihao/nihao-users2/yuhao/DSLP/env/ctcdecode/ctcdecode/src/ctc_beam_search_decoder.cpp:32] FATAL: "(probs_seq[i].size()) == (vocabulary.size())" check failed. The shape of probs_seq does not mat…
-
**Describe the bug**
"speech_to_text_bpe.py"(ASR example) with ddp (8-gpus) failed to run.
It produced a "RuntimeError: CUDA error: all CUDA-capable devices are busy or unavailable"
**Steps/Cod…
-
Hi,
How to load the trained model and inference? Thanks in advance.
-
I'm trying to use: https://github.com/microsoft/unilm/tree/master/decoding/GAD with pre-trained model in that repo for inference
Description: wmt14.en-de
Models:
- [at-verifier-base](https://driv…
-
Hi,
after some unsuccessful training, when I restart the training again, I keep receivinig error report saying:
`ERROR Unexpected exception: no checkpoints found in ...`
Even if i reinstall…
-
Related to **Model/Framework(s)**
PyTorch/Translation/Transformer
**Describe the bug**
I followed by the instructions in README.md but found this issue.
Tue Aug 8 23:35:31 2023
+------…
-
Hello,
Sorry, my background is in img generation (SD) but I'm trying to get into voice synthetisation. This may be a simple fix, but this is the error I receive when I attempt to begin training a m…
-
Hey, thanks for interesting work.
I was trying to run train_story.sh, but was running into memory issues when running on NVIDIA V100. Would you be able to share the configurations that you ran it on,…
-
I installed k2 using Conda on centos, but also encounter the import error. Tried the method described in Note , but it didn't work either. What can I do to solve it?
Traceback (most recent call las…