lingvo
lingvo copied to clipboard
tensorflow
Lingvo
I am training a Lingvo ASR model from scratch on the Librispeech 100 dataset, where Lingvo is installed via `pip`. The training environment uses a single GPU. I am running...
Hi there, I have a fork of lingvo that has been very useful for my team's work for a while now. I recently noticed that REGISTER_OP("AsciiToTokenId") in x_ops.cc is missing...
Hi! Is there a guide to implement MWER Training in lingvo? I have tried to write the code from scratch, but it is a really difficult to me. I'm trying...
the code for mwer is in which file
Hi Lingvo, thanks for releasing this awesome OSS. I am trying it out for the first time following this codelab: https://colab.research.google.com/github/tensorflow/lingvo/blob/master/codelabs/introduction.ipynb I am getting about 0.2 steps/s on a single...
Modifying the code is a bit of a hassle when I have many pylint warnings from the existing code. Can you upload the pylintrc file that you already use for...
I've noticed that the rnn code in lingvo (in particular for ASR tasks) uses bitmasks for representing the validity of data in a sequence when you do batching. To be...
I used `generate_waymo_tf.py` to generate the tf.EXAMPLE for training StarNet model. But I'm not sure about the output format. As far as I understand, each segment in Waymo will result...
Hi, Could someone help me understand how the evaluation works. Even with 1 validation sample in the directory, I still seem to see total examples to be done as 40007...
I am getting the following error on running waymo vehicle model on google cloud. I am using model=params.waymo.StarNetVehicle error occurs in decoder part. 2020-04-12T10:09:46.622604Z Imported params.waymo I 2020-04-12T10:09:46.622740Z Known model:...
