-
Hi, I'm using the fork command on am_resnet_ctc_librispeech_dev_other.bin to adapt the model to my own dataset, and i got the following errors which says `Loss has NaN values.`
```
I0723 11:44:53.26…
-
I have trained conv_glu (wav2letter) 2016 with feature extracted from wav2vec model.
I choose the learning rate = 1.0 and batchsize = 36 with dataset over 500 hours voice audio.
But WER didn't conv…
-
Below is my coding
https://github.com/epona7471/YoonKang.github.io/blob/main/install.ipynb
(followed by guide line at https://github.com/mailong25/self-supervised-speech-recognition/blob/master/De…
-
I finally managed to get wav2letter compiled on my system (heaven knows if the build was valid, but it finished).
When I try the tutorial it looks like it runs for 1 epoch/iteration and then crash…
-
Thank You for providing such a proper guide to install python bindings for wav2letter..
I have been trying to follow https://github.com/facebookresearch/wav2letter/wiki/Python-bindings but could not …
-
in \knausj_talon\misc\desktops.talon
on Windows 10:
'desk two' does not work. Command registers, nothing happens. no errors appear in log
```
main | engine.phrase desk two
talon_plugins.subt…
-
I came across this issue while attempting to convert Meta's Wav2Letter model to .onnx format. From some preliminary investigation, it seems that in cases where a model has the ExpandDims operator in t…
-
### Feature Description
I'd like to be able to use FeatureTransforms without sfx/libsoundfile compiled in.
#### Use Case
I use flashlight/wav2letter without libsndfile, so the hard dependency fro…
-
### Bug Description
I am trying to reproduce the lexicon free speech recognition on librispeech dataset (clean). So as per the given instructions [recipes/models/lexicon_free](https://github.com/face…
-
The layout of the conv2d and linear layers in your encoder end up cramping the output tokens:
```
forward torch.Size([32, 1600, 80])
self.encode torch.Size([32, 99, 1216])
self.linear …