update with whisperx

cog.yaml

@@ -4,30 +4,21 @@
 build:
   gpu: true
   system_packages:
-    - "libgl1-mesa-glx"
-    - "libglib2.0-0"
+    - libgl1-mesa-glx
+    - libglib2.0-0
     - ffmpeg
     - espeak-ng
-  python_version: "3.9.16"
+  python_version: "3.11"
   python_packages:
-    - torch==2.0.1
-    - torchaudio==2.0.2 
-    - xformers==0.0.22
-    - tensorboard==2.16.2
+    - torch==2.1.0
+    - torchaudio==2.1.0 
+    - xformers
     - phonemizer==3.2.1
-    - datasets==2.16.0
-    - torchmetrics==0.11.1
     - whisperx==3.1.1
     - openai-whisper>=20231117
   run:
-    - curl -O https://repo.anaconda.com/miniconda/Miniconda3-py310_23.3.1-0-Linux-x86_64.sh
-    - bash Miniconda3-py310_23.3.1-0-Linux-x86_64.sh -b -p /cog/miniconda
-    - /cog/miniconda/bin/conda init bash
-    - /bin/bash -c "source /cog/miniconda/bin/activate && conda create -n myenv python=3.9.16 -y"
-    - /bin/bash -c "source /cog/miniconda/bin/activate && conda activate myenv && conda install -c conda-forge montreal-forced-aligner=2.2.17 openfst=1.8.2 kaldi=5.5.1068 -y"
-    - /bin/bash -c "source /cog/miniconda/bin/activate && conda activate myenv && mfa model download dictionary english_us_arpa &&  mfa model download acoustic english_us_arpa"
-    - export PATH=/cog/miniconda/envs/myenv/bin:$PATH
     - git clone https://github.com/facebookresearch/audiocraft && pip install -e ./audiocraft
     - pip install "pydantic<2.0.0"
     - curl -o /usr/local/bin/pget -L "https://github.com/replicate/pget/releases/download/v0.6.0/pget_linux_x86_64" && chmod +x /usr/local/bin/pget
-predict: "predict.py:Predictor"
+    - mkdir -p /root/.cache/torch/hub/checkpoints/ && wget --output-document "/root/.cache/torch/hub/checkpoints/wav2vec2_fairseq_base_ls960_asr_ls960.pth" "https://download.pytorch.org/torchaudio/models/wav2vec2_fairseq_base_ls960_asr_ls960.pth"
+predict: "predict.py:Predictor"