The speech recognition model is just one of the models in the Tensor2Tensor library. Tensor2Tensor (T2T) is a library of deep learning models and datasets as well as a set of scripts that allow you to train the models and to download and prepare the data. This model does speech-to-text conversion.
Before you begin
Before starting this tutorial, follow the steps below to check that your Google Cloud project is correctly set up.
Sign in to your Google Account.
If you don't already have one, sign up for a new account.
In the Cloud Console, on the project selector page, select or create a Cloud project.
Make sure that billing is enabled for your Google Cloud project. Learn how to confirm billing is enabled for your project.
This walkthrough uses billable components of Google Cloud. Check the Cloud TPU pricing page to estimate your costs. Be sure to clean up resources you create when you've finished with them to avoid unnecessary charges.
Set up your resources
This section provides information on setting up Cloud Storage storage, VM, and Cloud TPU resources for tutorials.
Create a Cloud Storage bucket
You need a Cloud Storage bucket to store the data you use to train
your model and the training results. The
ctpu up tool used in this tutorial
sets up default permissions for the Cloud TPU service account. If you want
finer-grain permissions, review the access level permissions.
The bucket location must be in the same region as your virtual machine (VM) and your TPU node. VMs and TPU nodes are located in specific zones, which are subdivisions within a region.
Go to the Cloud Storage page on the Cloud Console.
Create a new bucket, specifying the following options:
- A unique name of your choosing.
Regionfor Location type and
us-central1for the Location (zone)
- Default storage class:
- Location: Specify a bucket location in the same region where you plan to create your TPU node. See TPU types and zones to learn where various TPU types are available.
This section demonstrates using the Cloud TPU provisioning
creating and managing Cloud TPU project resources. The
resources are comprised of a virtual machine (VM) and a Cloud TPU
resource that have the same name. These resources
must reside in the same region/zone as the bucket you just created.
You can also set up your VM and TPU resources using
gcloud commands or through
the Cloud Console. See the
creating and deleting TPUs page
to learn all the ways you can set up and manage your Compute Engine VM
and Cloud TPU resources.
ctpu up to create resources
Open a Cloud Shell window.
gcloud config set project <var>your-project</var>to set the project where you want to create Cloud TPU.
ctpu upspecifying the flags shown for either a Cloud TPU device or Pod slice. If you do not specify
tpu-size, the default is a v2-8 Cloud TPU. Refer to CTPU Reference for flag options and descriptions.
Set up a Cloud TPU device:
$ ctpu up
The configuration you specified appears. Enter y to approve or n to cancel.
ctpu upcommand has finished executing, verify that your shell prompt has changed from
username@vm-name. This change shows that you are now logged into your Compute Engine VM.
gcloud compute ssh vm-name --zone=us-central1-b \ (vm)$ export TPU_NAME=tpu-name
As you continue these instructions, run each command that
(vm)$ in your VM session window.
Add disk space to your VM
T2T conveniently packages data generation for many common open-source datasets
t2t-datagen script. The script downloads the data, preprocess it, and
makes it ready for training. To do so, it needs local disk space.
You can skip this step if you used
ctpu up to create your
Compute Engine VM since it provides 250 GB of disk space for your VM.
If you set up your Compute Engine VM using
gcloud commands or the
Cloud Console, and did not specify the VM disk size to be at least 200 GB,
follow the instructions below.
- Follow the Compute Engine guide to add a disk to your Compute Engine VM.
- Set the disk size to 200 GB (the recommended minimum size).
- Set When deleting instance to Delete disk to ensure that the disk is removed when you remove the VM.
Make a note of the path to your new disk. For example:
Generate the training and evaluation datasets
On your Compute Engine VM:
Create the following environment variables for directories:
(vm)$ STORAGE_BUCKET=gs://YOUR-BUCKET-NAME (vm)$ DATA_DIR=$STORAGE_BUCKET/data/ (vm)$ OUT_DIR=$STORAGE_BUCKET/OUT_DIR (vm)$ export TMP_DIR=YOUR-TMP-DIRECTORY
YOUR-BUCKET-NAMEis the name of your Cloud Storage bucket.
DATA_DIRis a location on Cloud Storage that holds the training and evaluation data.
OUT_DIRspecifies the directory where checkpoints and summaries are stored during model training. If the folder is missing, the program creates one. When using a Cloud TPU, the
output_dirmust be a Cloud Storage path (
gs://...). You can reuse an existing folder to load current checkpoint data and to store additional checkpoints.
YOUR-TMP_DIRECTORYis a location to use to store temporary data. If you added a disk to your Compute Engine VM, this will be a location on the added disk (for example,
/mnt/disks/mnt-dir/t2t_tmp. Otherwise, it will be a temporary directory on your VM (for example,
If you added a new disk to your Compute Engine VM, create a temporary directory on the added disk.
(vm)$ mkdir $TMP_DIR
t2t-datagenscript to generate both the full dataset and the small clean version, which you will use for evaluation.
The audio import in
soxto generate normalized waveforms. Install it on your Compute Engine VM and then run the
t2t-datagencommands that follow.
(vm)$ sudo apt-get install sox
(vm)$ t2t-datagen --problem=librispeech --data_dir=$DATA_DIR --tmp_dir=$TMP_DIR (vm)$ t2t-datagen --problem=librispeech_clean --data_dir=$DATA_DIR --tmp_dir=$TMP_DIR
librispeech_train_full_test_clean trains on the full dataset
but evaluate on the clean dataset.
You can also use
librispeech_clean_small which is a small version
of the clean dataset.
You can view the data on Cloud Storage by going to the Google Cloud Console and choosing Storage from the left-hand menu. Click the name of the bucket that you created for this tutorial.
Training the model
To train a model on Cloud TPU run the trainer with big batches and truncated sequences.
(vm)$ t2t-trainer \ --model=transformer \ --hparams_set=transformer_librispeech_tpu \ --problem=librispeech_train_full_test_clean \ --train_steps=210000 \ --eval_steps=3 \ --local_eval_frequency=100 \ --data_dir=$DATA_DIR \ --output_dir=$OUT_DIR \ --use_tpu \ --cloud_tpu_name=$TPU_NAME
After this step is completed, run the training again for more steps with
smaller batch size and full sequences. This training take approximately 11
hours on a
v3-8 TPU node.
(vm)$ t2t-trainer \ --model=transformer \ --hparams_set=transformer_librispeech_tpu \ --hparams=max_length=295650,max_input_seq_length=3650,max_target_seq_length=650,batch_size=6 \ --problem=librispeech_train_full_test_clean \ --train_steps=230000 \ --eval_steps=3 \ --local_eval_frequency=100 \ --data_dir=$DATA_DIR \ --output_dir=$OUT_DIR \ --use_tpu \ --cloud_tpu_name=$TPU_NAME
To avoid incurring charges to your GCP account for the resources used in this topic:
Disconnect from the Compute Engine VM:
Your prompt should now be
username@projectname, showing you are in the Cloud Shell.
In your Cloud Shell, run
ctpu deletewith the --zone flag you used when you set up the Cloud TPU to delete your Compute Engine VM and your Cloud TPU:
$ ctpu delete [optional: --zone]
ctpu statusto make sure you have no instances allocated to avoid unnecessary charges for TPU usage. The deletion might take several minutes. A response like the one below indicates there are no more allocated instances:
$ ctpu status --zone=europe-west4-a
2018/04/28 16:16:23 WARNING: Setting zone to "--zone=europe-west4-a" No instances currently exist. Compute Engine VM: -- Cloud TPU: --
gsutilas shown, replacing bucket-name with the name of the Cloud Storage bucket you created for this tutorial:
$ gsutil rm -r gs://bucket-name
- Learn more about
ctpu, including how to install it on a local machine.
- Explore more Tensor2Tensor models for TPU.
- Experiment with more TPU samples.
- Explore the TPU tools in TensorBoard.