diff --git a/.compute b/.compute index 60e4ff2e..6552bfb2 100755 --- a/.compute +++ b/.compute @@ -7,7 +7,7 @@ python3 -m venv /tmp/venv source /tmp/venv/bin/activate pip install -r <(grep -v tensorflow requirements.txt) -pip install tensorflow-gpu==1.14.0 +pip install tensorflow-gpu==1.15.0 # Install ds_ctcdecoder package from TaskCluster pip install $(python3 util/taskcluster.py --decoder) diff --git a/doc/TRAINING.rst b/doc/TRAINING.rst index ca0160e1..81553494 100644 --- a/doc/TRAINING.rst +++ b/doc/TRAINING.rst @@ -64,7 +64,7 @@ If you have a capable (NVIDIA, at least 8GB of VRAM) GPU, it is highly recommend .. code-block:: bash pip3 uninstall tensorflow - pip3 install 'tensorflow-gpu==1.14.0' + pip3 install 'tensorflow-gpu==1.15.0' Please ensure you have the required `CUDA dependency `_. @@ -75,7 +75,7 @@ It has been reported for some people failure at training: tensorflow.python.framework.errors_impl.UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[{{node tower_0/conv1d/Conv2D}}]] -Setting the ``TF_FORCE_GPU_ALLOW_GROWTH`` environment variable to ``true`` seems to help in such cases. This could also be due to an incorrect version of libcudnn. Double check your versions with the `TensorFlow 1.14 documentation `_. +Setting the ``TF_FORCE_GPU_ALLOW_GROWTH`` environment variable to ``true`` seems to help in such cases. This could also be due to an incorrect version of libcudnn. Double check your versions with the `TensorFlow 1.15 documentation `_. Common Voice training data ^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -185,7 +185,7 @@ TensorFlow has tooling to achieve this: it requires building the target ``//tens .. code-block:: - $ python3 util/taskcluster.py --source tensorflow --artifact convert_graphdef_memmapped_format --branch r1.14 --target . + $ python3 util/taskcluster.py --source tensorflow --artifact convert_graphdef_memmapped_format --branch r1.15 --target . Producing a mmap-able model is as simple as: diff --git a/doc/USING.rst b/doc/USING.rst index 915e77e8..9769d386 100644 --- a/doc/USING.rst +++ b/doc/USING.rst @@ -23,7 +23,7 @@ Please refer to your system's documentation on how to install these dependencies CUDA dependency ^^^^^^^^^^^^^^^ -The GPU capable builds (Python, NodeJS, C++, etc) depend on the same CUDA runtime as upstream TensorFlow. Currently with TensorFlow 1.14 it depends on CUDA 10.0 and CuDNN v7.5. `See the TensorFlow documentation `_. +The GPU capable builds (Python, NodeJS, C++, etc) depend on the same CUDA runtime as upstream TensorFlow. Currently with TensorFlow 1.15 it depends on CUDA 10.0 and CuDNN v7.5. `See the TensorFlow documentation `_. Getting the pre-trained model ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/native_client/README.rst b/native_client/README.rst index 373b5efd..a249a716 100644 --- a/native_client/README.rst +++ b/native_client/README.rst @@ -5,7 +5,7 @@ Building DeepSpeech Binaries If you'd like to build the DeepSpeech binaries yourself, you'll need the following pre-requisites downloaded and installed: -* `Mozilla's TensorFlow r1.14 branch `_ +* `Mozilla's TensorFlow r1.15 branch `_ * `General TensorFlow requirements `_ * `libsox `_ @@ -32,7 +32,7 @@ Clone our fork of TensorFlow and checkout the correct version: .. code-block:: git clone https://github.com/mozilla/tensorflow.git - git checkout origin/r1.14 + git checkout origin/r1.15 Bazel: Download & Install ^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/native_client/dotnet/README.rst b/native_client/dotnet/README.rst index 6a21d20a..70fdbf3d 100644 --- a/native_client/dotnet/README.rst +++ b/native_client/dotnet/README.rst @@ -51,7 +51,7 @@ We need to clone ``mozilla/DeepSpeech`` and ``mozilla/tensorflow``. .. code-block:: bash - git clone --branch r1.14 https://github.com/mozilla/tensorflow + git clone --branch r1.15 https://github.com/mozilla/tensorflow Configuring the paths --------------------- diff --git a/taskcluster/test-training_16k-linux-amd64-py36m-opt.yml b/taskcluster/test-training_16k-linux-amd64-py36m-opt.yml index d8cb4613..fac0ea98 100644 --- a/taskcluster/test-training_16k-linux-amd64-py36m-opt.yml +++ b/taskcluster/test-training_16k-linux-amd64-py36m-opt.yml @@ -7,7 +7,7 @@ build: apt-get -qq -y install ${python.packages_trusty.apt} args: tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/taskcluster/tc-train-tests.sh 3.6.4:m 16k" - convert_graphdef: "https://index.taskcluster.net/v1/task/project.deepspeech.tensorflow.pip.r1.14.351a98ab6e60c2bf257f05e515a420aba3027d8b.cpu/artifacts/public/convert_graphdef_memmapped_format" + convert_graphdef: "https://community-tc.services.mozilla.com/api/index/v1/task/project.deepspeech.tensorflow.pip.r1.15.ceb46aae5836a0f648a2c3da5942af2b7d1b98bf.cpu/artifacts/public/convert_graphdef_memmapped_format" metadata: name: "DeepSpeech Linux AMD64 CPU 16kHz training Py3.6" description: "Training a DeepSpeech LDC93S1 model for Linux/AMD64 16kHz Python 3.6, CPU only, optimized version" diff --git a/taskcluster/test-training_8k-linux-amd64-py36m-opt.yml b/taskcluster/test-training_8k-linux-amd64-py36m-opt.yml index 8d5c6de4..1212aea2 100644 --- a/taskcluster/test-training_8k-linux-amd64-py36m-opt.yml +++ b/taskcluster/test-training_8k-linux-amd64-py36m-opt.yml @@ -7,7 +7,7 @@ build: apt-get -qq -y install ${python.packages_trusty.apt} args: tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/taskcluster/tc-train-tests.sh 3.6.4:m 8k" - convert_graphdef: "https://index.taskcluster.net/v1/task/project.deepspeech.tensorflow.pip.r1.14.351a98ab6e60c2bf257f05e515a420aba3027d8b.cpu/artifacts/public/convert_graphdef_memmapped_format" + convert_graphdef: "https://community-tc.services.mozilla.com/api/index/v1/task/project.deepspeech.tensorflow.pip.r1.15.ceb46aae5836a0f648a2c3da5942af2b7d1b98bf.cpu/artifacts/public/convert_graphdef_memmapped_format" metadata: name: "DeepSpeech Linux AMD64 CPU 8kHz training Py3.6" description: "Training a DeepSpeech LDC93S1 model for Linux/AMD64 8kHz Python 3.6, CPU only, optimized version"