-
I've been running the examples in the "conformer/" and in the "rnn_transducer/" directories and comparing the models with those already provided on drive.
The conformer training works as expected, …
-
This issue is to track the follow-up work to #1137, which introduced `rnnt_loss` and `RNNTLoss` as a [prototype](https://pytorch.org/audio/stable/index.html) in `torchaudio.prototype.transducer` using…
-
The transducer in TensorFlowASR\examples\rnn_transducer doesn't work for the current version with either current or pretrained config.yml. This is a fundamental function. Can the author or someone giv…
-
Hello,
Im trying to convert a pertained model trained on librispeech, but I run into the following error
```
tensorflow.lite.python.convert_phase.ConverterError: input resource[0] expected type r…
-
Does lingvo include the RNN-Transducer loss computation ?
-
-
Hello guys,
In this article https://arxiv.org/pdf/2104.11127.pdf there is very simple idea of how to adapt RNN-T to the unknown text.
The writer of the article reports about very nice WER impro…
-
The architecture in the paper suggests unidirectional RNNs. Is there any reason why you used bidirectional RNNs in neural_transducer.py ?
-
The name `Rnnt` in the code is confusing. We are not using recurrent connections (i.e., RNN, GRU, LSTM) in our transducer models and we should use `transducer` to replace `Rnnt` in the code.
-
I am trying to understand the requirements on the RNNLM for LODR rescoring
I am using something along the lines of Librispeech pruned_transducer_stateless3 recipe with
https://github.com/k2-fsa/ic…