name: export-whisper-to-onnx

on:
  workflow_dispatch:

concurrency:
  group: release-whisper-${{ github.ref }}
  cancel-in-progress: true

jobs:
  release-whisper-models:
    if: github.repository_owner == 'k2-fsa' || github.repository_owner == 'csukuangfj'
    name: ${{ matrix.model }}
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: false
      matrix:
        os: [ubuntu-latest]
        model: ["distil-medium.en", "tiny.en", "base.en", "small.en", "medium.en", "tiny", "base", "small", "medium", "large", "large-v1", "large-v2"]
        python-version: ["3.8"]

    steps:
      - uses: actions/checkout@v4

      - name: Setup Python ${{ matrix.python-version }}
        uses: actions/setup-python@v2
        with:
          python-version: ${{ matrix.python-version }}

      - name: Install dependencies
        shell: bash
        run: |
          python3 -m pip install torch==1.13.0 -f https://download.pytorch.org/whl/cpu/torch_stable.html
          python3 -m pip install openai-whisper==20230314 onnxruntime onnx

      - name: export ${{ matrix.model }}
        shell: bash
        run: |
          cd scripts/whisper
          model=${{ matrix.model }}
          echo "model: $model"
          if [[ $model == distil-medium.en ]]; then
            wget -q -O distil-medium-en-original-model.bin https://huggingface.co/distil-whisper/distil-medium.en/resolve/main/original-model.bin
            ls -lh
          fi
          python3 ./export-onnx.py --model ${{ matrix.model }}
          # python3 -m onnxruntime.tools.convert_onnx_models_to_ort --optimization_style=Fixed ./

          ls -lh

          if [[ $model != distil-medium.en ]]; then
            ls -lh ~/.cache/whisper
          fi

          src=sherpa-onnx-whisper-${{ matrix.model }}

          mkdir $src
          cp *.onnx $src/
          cp *tokens.txt $src

          cd $src
          mkdir -p test_wavs
          cd test_wavs
          wget -q https://huggingface.co/csukuangfj/sherpa-onnx-whisper-medium.en/resolve/main/test_wavs/0.wav
          wget -q https://huggingface.co/csukuangfj/sherpa-onnx-whisper-medium.en/resolve/main/test_wavs/1.wav
          wget -q https://huggingface.co/csukuangfj/sherpa-onnx-whisper-medium.en/resolve/main/test_wavs/8k.wav
          wget -q https://huggingface.co/csukuangfj/sherpa-onnx-whisper-medium.en/resolve/main/test_wavs/trans.txt
          cd ../..
          mv $src ../..

          cd ../..
          echo "--------------------"
          ls -lh
          ls -lh $src
          echo "--------------------"

          tar cjvf ./$src.tar.bz2 $src

      - name: Release
        uses: svenstaro/upload-release-action@v2
        with:
          file_glob: true
          file: ./*.tar.bz2
          overwrite: true
          repo_name: k2-fsa/sherpa-onnx
          repo_token: ${{ secrets.UPLOAD_GH_SHERPA_ONNX_TOKEN }}
          tag: asr-models

      - name: Publish ${{ matrix.model }} to huggingface
        shell: bash
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN }}
        run: |
          src=sherpa-onnx-whisper-${{ matrix.model }}

          git config --global user.email "csukuangfj@gmail.com"
          git config --global user.name "Fangjun Kuang"

          GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/csukuangfj/sherpa-onnx-whisper-${{ matrix.model }} huggingface
          rm -rf huggingface/*

          cp -av $src/* ./huggingface/

          cd huggingface

          git status
          ls -lh
          git lfs track "*.onnx"
          # git lfs track "*.ort"
          git add .
          git commit -m "upload ${{ matrix.model }}"
          git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/sherpa-onnx-whisper-${{ matrix.model }} main