-
### Describe the bug
Originally reported by #1867
`ValueError: Found inputs tensors to be on [device(type='cuda', index=0), device(type='cuda', index=0), device(type='cuda', index=0), device(typ…
-
Racket newcomers are immediately confronted with four equality operators:
- `equal?`, which does what you'd expect most of the time
- `=`, which does what you'd expect if you're used to IEEE numbe…
-
### What happened?
Hi there,
First of all, thank you for developing PySR! I have been experimenting with it and wanted to test it on the Nguyen benchmark problems, such as `x^3+x^2+x`. In order …
-
When i try to train a Transducer model, i can't successfully run the main.py. I meet the error as following:
Traceback (most recent call last):
File "main.py", line 222, in
main(0, args)
…
-
Hi,
I am having problems running a uODE in SciML. Whenever I run my script in `REPL` of `vscode` I do not get errors.
When I run the script in the terminal with `julia ./script.jl` I get a seg…
-
Hello, could you please give a reference configuration for the ensemble transducer model in [the example repository](https://github.com/k2-fsa/sherpa/tree/master/triton/model_repo_streaming/transducer…
-
It seems that the training stuck in the wee hours of the morning today. Any suggestion ?
```
2023-05-23 02:56:53,214 INFO [train_tt.py:1100] (0/3) Computing validation loss
2023-05-23 02:56:53,21…
-
Hi,
I need to use _speaker diarization_ in a pipeline with ASR for Slovenian language. For the speech recognition I use a highly accurate `CTC Conformer` model.
At first, I tried to employ p…
-
My utimate goal is to compare wenet and k2 on online streaming situation for my team. To convince my team come to k2 for online streaming.
But I'm stuck on the first step: finetuning gigaspeech pre…
-
### Model description
paper: [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://arxiv.org/abs/2002.02562)
- Transformer-Transducer i…