-
hello, everyone. I have been installing sherpa and when I wanted to run streaming server.py. encounter with this error,
![Uploading image.png…]()
-
When I was trying a zipformer (pruned_transducer_stateless7) on spgispeech, I did the following:
```
python pruned_transducer_stateless7/train.py --world-size 2 --max-duration 250
```
I got the fo…
-
### System Info
system info
OS: Ubuntu 18.04.6 LTS
GPUS: RTX 3090 * 2
CUDA: 11.1
python: 3.8
transformers: 4.23.1
pytorch: 1.10.1+cu111
NCCL: 2.10.3+cuda11.1
### Who can help?
@sgugg…
-
Hello guys,
I have a question regarding tedlium3 recipe tensorboard.
What are meanings of the following values:
current_loss
current_pruned_loss
current_simple_loss
tot_loss
Thanks very…
-
It is suprising that no one has noticed that the current code is feeding the output of
log_softmax to torchaudio's rnnt_loss, which is not correct.
torchaudio's rnnt_loss accepts only `logits` as…
-
the pretrained model got from
https://github.com/espnet/espnet/tree/master/egs2/librispeech/asr1
Conformer-RNN Transducer
Environments
date: Wed Apr 27 09:30:57 EDT 2022
python version: 3.8.5 (d…
-
**Describe the bug**
Dear developers,
I met some problems while applying the fine-tuning asr model to decode the test set, and I found no further information on solving this bug. Thanks for helping…
-
This scary error sometimes greets you if you are using the transformer:
```
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [398,0,0], thread: [51,0,0] Assertion `index >= -size…
-
Hi wenet team,
I want to know more details about the [RNN-T result](https://github.com/wenet-e2e/wenet/blob/main/examples/aishell/rnnt/README.md).
Just list the last table here:
| rnnt | ctc …
-
Transducer training on GPU raises an error because it encounters a mixed CPU/GPU operation. Sample trace:
```
Epoch 0: 0%| | 0/294 [00:00