Merge branch 'main' into dev_1.17.0

Author: beat-buesser

.github/actions/deepspeech-v2/Dockerfile

@@ -1,5 +1,5 @@
-# Get base from a pytorch image
-FROM pytorch/pytorch:1.6.0-cuda10.1-cudnn7-runtime
+pod# Get base from a pytorch image
+FROM pytorch/pytorch:2.1.1-cuda12.1-cudnn8-runtime
 
 # Set to install things in non-interactive mode
 ENV DEBIAN_FRONTEND noninteractive
@@ -17,26 +17,19 @@ RUN apt-get update \
         curl \
         libsndfile-dev \
         libsndfile1 \
+        vim \
+        curl \
      && apt-get clean all \
      && rm -r /var/lib/apt/lists/*
 
-RUN /opt/conda/bin/conda install --yes \
-    astropy \
-    matplotlib \
-    pandas \
-    scikit-learn \
-    scikit-image
-
 # Install necessary libraries for deepspeech v3
-RUN pip install torch
-RUN pip install tensorflow
-RUN pip install torchaudio==0.6.0
-RUN pip install --no-build-isolation fairscale
+RUN pip install --ignore-installed PyYAML torch==2.1.1 tensorflow==2.14.1 torchaudio==2.1.1 pytorch-lightning==2.1.2 scikit-learn==1.3.2
+RUN pip install --no-build-isolation fairscale==0.4.13
 
 RUN git clone https://github.com/SeanNaren/deepspeech.pytorch.git
-RUN cd deepspeech.pytorch && pip install -r requirements.txt
-RUN cd deepspeech.pytorch && pip install -e .
+RUN cd deepspeech.pytorch && sed -i '/^sklearn/d' requirements.txt && pip install -r requirements.txt && pip install -e .
+
+RUN pip install numba==0.56.4 pytest-cov==4.1.0 pydub==0.25.1
+RUN pip list
 
-RUN pip install numba==0.50.0
-RUN pip install pytest-cov
-RUN pip install pydub==0.25.1
+RUN mkdir -p /root/.art/data && cd /root/.art/data && curl -LJO "https://github.com/SeanNaren/deepspeech.pytorch/releases/download/V3.0/librispeech_pretrained_v3.ckpt"

.github/actions/deepspeech-v2/action.yml

@@ -23,9 +23,9 @@ on:
 
 jobs:
   test_deepspeech_v3_torch_1_10:
-    name: PyTorchDeepSpeech v3 / PyTorch 1.10
+    name: PyTorchDeepSpeech v3 / PyTorch 2.1.1
     runs-on: ubuntu-latest
-    container: adversarialrobustnesstoolbox/art_testing_envs:deepspeech_v3_torch_1_10
+    container: adversarialrobustnesstoolbox/art_testing_envs:deepspeech_v3_torch_2_1_1
     steps:
       - name: Checkout Repo
         uses: actions/checkout@v3

.github/actions/deepspeech-v2/run.sh

@@ -41,7 +41,7 @@ jobs:
       - name: Checkout Repo
         uses: actions/checkout@v3
       - name: Setup Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
       - name: Install Dependencies

.github/actions/deepspeech-v3/Dockerfile

@@ -52,7 +52,7 @@ jobs:
       - name: Checkout Repo
         uses: actions/checkout@v3
       - name: Setup Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
       - name: Install Dependencies

.github/workflows/ci-deepspeech-v2.yml

@@ -44,7 +44,7 @@ jobs:
       - name: Checkout Repo
         uses: actions/checkout@v3
       - name: Setup Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
       - name: Install Dependencies

.github/workflows/ci-deepspeech-v3.yml

@@ -41,7 +41,7 @@ jobs:
       - name: Checkout Repo
         uses: actions/checkout@v3
       - name: Setup Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
       - name: Pre-install Lingvo ASR
@@ -50,7 +50,7 @@ jobs:
           sudo apt-get update
           sudo apt-get -y -q install ffmpeg libavcodec-extra
           python -m pip install --upgrade pip setuptools wheel
-          pip install -q -r <(sed '/^scipy/d;/^matplotlib/d;/^pandas/d;/^statsmodels/d;/^numba/d;/^jax/d;/^h5py/d;/^Pillow/d;/^pytest/d;/^pytest-mock/d;/^torch/d;/^torchaudio/d;/^torchvision/d;/^xgboost/d;/^requests/d;/^tensorflow/d;/^keras/d;/^kornia/d;/^librosa/d;/^tqdm/d;/^timm/d' requirements_test.txt)
+          pip install -q -r <(sed '/^scipy/d;/^matplotlib/d;/^pandas/d;/^statsmodels/d;/^numba/d;/^jax/d;/^h5py/d;/^Pillow/d;/^pytest/d;/^pytest-mock/d;/^torch/d;/^torchaudio/d;/^torchvision/d;/^xgboost/d;/^requests/d;/^tensorflow/d;/^keras/d;/^kornia/d;/^librosa/d;/^tqdm/d;/^timm/d;/^catboost/d' requirements_test.txt)
           pip install scipy==1.5.4
           pip install matplotlib==3.3.4
           pip install pandas==1.1.5
@@ -74,6 +74,7 @@ jobs:
           pip install kornia==0.6.8
           pip install librosa==0.9.2
           pip install tqdm==4.64.1
+          pip install catboost==1.1.1
           pip list
       - name: Run ${{ matrix.name }} Tests
         run: pytest --cov-report=xml --cov=art --cov-append -q -vv tests/estimators/speech_recognition/test_tensorflow_lingvo.py --framework=${{ matrix.framework }} --durations=0