Open q121q opened 4 years ago
Alex, I would suggest:
pip install lingvo
or from source.lingvo/tasks/asr/tools
in order (librispeech.01.download_train.sh
, librispeech.02.download_devtest.sh
and so forth.bazel-bin/lingvo/trainer --run_locally=cpu --mode=sync --model=librispeech.Librispeech960Wpm --decoder_jobs=dev,test --job=controller,trainer_client,decoder_test,decoder_dev,evaler_test,evaler_dev --logdir=/tmp/logdir --logtostderr
. See the MT example for a more elaborate scenario.params.encoder.use_specaugment = True
in Task()
(see the definition). You can further configure it using specaugment_network
.
Hello,
I want to train an ASR system using the specaugment idea, however I have low experience with tensorflow & lingvo. What is the proposed way to move forward with this? From what I looked there's no end-to-end recipe, is there any other repo that contains such recipe?
Thanks!