Merge branch 'main' into text_generation_improvement

.github/labeler.yml

@@ -0,0 +1,33 @@
+ASR:
+- nemo/collections/asr/**/*
+- examples/asr/**/*
+- tutorials/asr/**/*
+- docs/source/asr/**/*
+
+NLP:
+- nemo/collections/nlp/**/*
+- examples/nlp/**/*
+- tutorials/nlp/**/*
+- docs/source/nlp/**/*
+
+Speaker Tasks:
+- examples/speaker_tasks/**/*
+- tutorials/speaker_tasks/**/*
+
+TTS:
+- nemo/collections/tts/**/*
+- examples/tts/**/*
+- tutorials/tts/**/*
+- docs/source/tts/**/*
+
+core:
+- nemo/core/**/*
+
+common:
+- nemo/collections/common/**/*
+
+CI:
+- .github/**/*
+- Jenkinsfile
+- Dockerfile
+- ci.groovy

.github/workflows/codeql.yml

@@ -0,0 +1,74 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ "main", "[rv][0-9]*",  "gh-pages-src" ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ "main" ]
+  schedule:
+    - cron: '19 1 * * 4'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v3
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v2
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # Details on CodeQL's query packs refer to : https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        queries: security-and-quality  # security-extended,
+
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, Go, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v2
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+
+    #   If the Autobuild fails above, remove it and uncomment the following three lines.
+    #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
+
+    # - run: |
+    #   echo "Run, Build Application using script"
+    #   ./location_of_script_within_repo/buildscript.sh
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v2
+      with:
+        category: "/language:${{matrix.language}}"

.github/workflows/labeler.yml

@@ -0,0 +1,14 @@
+name: "Pull Request Labeler"
+on:
+- pull_request_target
+
+jobs:
+  triage:
+    permissions:
+      contents: read
+      pull-requests: write
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/labeler@v4
+      with:
+        repo-token: "${{ secrets.GITHUB_TOKEN }}"

Dockerfile

@@ -14,7 +14,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-ARG BASE_IMAGE=nvcr.io/nvidia/pytorch:22.09-py3
+ARG BASE_IMAGE=nvcr.io/nvidia/pytorch:22.11-py3
 
 
 # build an image that includes only the nemo dependencies, ensures that dependencies
@@ -28,18 +28,18 @@ RUN apt-get update && \
     apt-get install -y \
     libsndfile1 sox \
     libfreetype6 \
-    python-setuptools swig \
-    python-dev ffmpeg && \
+    swig \
+    ffmpeg && \
     rm -rf /var/lib/apt/lists/*
 
 WORKDIR /tmp/
-RUN git clone https://github.com/NVIDIA/apex.git && \
+
+RUN git clone https://github.com/NVIDIA/apex.git -b 22.11-devel && \
     cd apex && \
-    git checkout 2b0e8371113fe70758f1964c40bf7dbe304fd9e6 && \
-    pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" --global-option="--fast_layer_norm" --global-option="--distributed_adam" --global-option="--deprecated_fused_adam" ./
+    pip3 install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" --global-option="--fast_layer_norm" --global-option="--distributed_adam" --global-option="--deprecated_fused_adam" ./
 
 # uninstall stuff from base container
-RUN pip uninstall -y sacrebleu torchtext
+RUN pip3 uninstall -y sacrebleu torchtext
 
 # build torchaudio
 WORKDIR /tmp/torchaudio_build
@@ -49,7 +49,7 @@ RUN /bin/bash /tmp/torchaudio_build/scripts/installers/install_torchaudio_latest
 # install nemo dependencies
 WORKDIR /tmp/nemo
 COPY requirements .
-RUN for f in $(ls requirements*.txt); do pip install --disable-pip-version-check --no-cache-dir -r $f; done
+RUN for f in $(ls requirements*.txt); do pip3 install --disable-pip-version-check --no-cache-dir -r $f; done
 
 # install pynini
 COPY nemo_text_processing/install_pynini.sh /tmp/nemo/
@@ -65,18 +65,19 @@ COPY . .
 
 # start building the final container
 FROM nemo-deps as nemo
-ARG NEMO_VERSION=1.13.0
+ARG NEMO_VERSION=1.14.0
 
 # Check that NEMO_VERSION is set. Build will fail without this. Expose NEMO and base container
 # version information as runtime environment variable for introspection purposes
 RUN /usr/bin/test -n "$NEMO_VERSION" && \
     /bin/echo "export NEMO_VERSION=${NEMO_VERSION}" >> /root/.bashrc && \
     /bin/echo "export BASE_IMAGE=${BASE_IMAGE}" >> /root/.bashrc
-# TODO: remove sed when PTL has updated their torchtext import check
-RUN --mount=from=nemo-src,target=/tmp/nemo cd /tmp/nemo && pip install ".[all]" && \
-    sed -i "s/_module_available(\"torchtext\")/False/g" /opt/conda/lib/python3.8/site-packages/pytorch_lightning/utilities/imports.py && \
-    python -c "import nemo.collections.asr as nemo_asr" && \
-    python -c "import nemo.collections.nlp as nemo_nlp" && \
+
+# Install NeMo
+RUN --mount=from=nemo-src,target=/tmp/nemo cd /tmp/nemo && pip install ".[all]"
+
+# Check install
+RUN python -c "import nemo.collections.nlp as nemo_nlp" && \
     python -c "import nemo.collections.tts as nemo_tts" && \
     python -c "import nemo_text_processing.text_normalization as text_normalization"