catalwaysright

> The support of Transducer models is not added to Riva yet. However you may convert these models to ONNX if you want. How can convert it to ONNX since...

> Then which part of code should I modify if I want to support this on my own. Could you give me a guide or a direction?

> @catalwaysright I'm working on word-level confidence for greedy CTC and RNNT decoding. Could you please describe your confidence use case? Basically I just want the word-level confidence like you...

@GNroy How is your implementation right now? Since we can get log prob for CTC, is it possible to get word-level prob though this?

> See #5 #6, and see the papers. Thanks for your reply! I have checked the issues and the paper. I just want to double check if I get it...

Another question is that I downloaded the `natural_questions` dataset to local but when I tried to load it using the load function provided in `data.py`, it showed that `Dataset path...

> How did you download NQ? > […](#) > On Sun, Mar 20, 2022 at 9:19 AM catalwaysright ***@***.***> wrote: Another question is that I downloaded the natural_questions dataset to...

Thank you so much for answering my questions so patiently! I encountered another problem when running `run_finetune.py` with the exactly same args as your experiment. However, I got cuda out...

> Sorry for bothering you again. Please show the specific place I should add `model.block_embedding_to("cpu")`, because when I add it after sending the model to GPU in `run_finetune.py`, it shows...

I tried your approach and is still shows cuda out of memory, but I figured it out that it may be normal because there is only 8G memory left on...