wav2letter

wav2letter copied to clipboard

Loading model files such as acoustic model | getting kenLM related issues for libraries

3

### Question I'm using Ubuntu 18.04 and using wav2letter v0.2 branch. I've successfully compile and built wav2letter on my machine. Now I'm working on building inference example as a standalone...

tumusudheer

For lexicon_free recipe: After creating a container, it is does not pass the test

17

### 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/facebookresearch/wav2letter/tree/v0.2/recipes/models/lexicon_free) I followed them and created the...

Trikaldarshi

Is python binding impossible?

1

### Question As your Important disclaimer, I accessed at flashlight (https://github.com/facebookresearch/flashlight) and build completely. At the stage of python bindings, I built flashlight and wanted to use it but i...

yuseungwoo

WAV2decoder package import error

1

### Question Hello I code like below, and it throws an error message. code - from wav2letter.decoder import CriterionType error - ModuleNotFoundError: No module named 'wav2letter' I am using windows...

SongGeunil1

Can i loaded wav2letter model and use it to serve (infer) as a service?

4

In the scense of service applications, we need to load model one time and serve for client request. But How can i do this?

phamvandan

Run the inference of Interactive Streaming ASR Example on Docker, we had this error?

1


phamvandan

[What is good learning rate and batchsize for training conv_glu (wav2letter) 2016? ]

4

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....

phamvandan

Could not start training 1-librispeech_clean as per given instructions

17

Hi, ``` OS: Ubuntu 18.04 Flashlight and Wave2Letter : Compiled from sources (master branch, just pulled today) Cuda: 10.2 (installed from cuda-repo-ubuntu1804-10-2-local-10.2.89-440.33.01_1.0-1_amd64.deb) cudnn: 7.6.5 ``` I'm following instructions as given...

tumusudheer

Tutorial Example seems to Fail?

5

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...

picheny-nyu

Higher Error Rate while Decoding

7

I have completed Training till 60 epochs on our own English dataset, we followed all the rules correctly and added the data and got the best acoustic model and have...

GowthamS07