name: export-nemo-giga-am-to-onnx

on:
  workflow_dispatch:

concurrency:
  group: export-nemo-giga-am-to-onnx-${{ github.ref }}
  cancel-in-progress: true

jobs:
  export-nemo-am-giga-to-onnx:
    if: github.repository_owner == 'k2-fsa' || github.repository_owner == 'csukuangfj'
    name: export nemo GigaAM models to ONNX
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: false
      matrix:
        os: [macos-latest]
        python-version: ["3.10"]

    steps:
      - uses: actions/checkout@v4

      - name: Setup Python ${{ matrix.python-version }}
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}

      - name: Run CTC
        shell: bash
        run: |
          pushd scripts/nemo/GigaAM
          ./run-ctc.sh
          popd

          d=sherpa-onnx-nemo-ctc-giga-am-russian-2024-10-24
          mkdir $d
          mkdir $d/test_wavs
          rm scripts/nemo/GigaAM/model.onnx
          mv -v scripts/nemo/GigaAM/*.int8.onnx $d/
          cp -v scripts/nemo/GigaAM/*.md $d/
          mv -v scripts/nemo/GigaAM/*.pdf $d/
          mv -v scripts/nemo/GigaAM/tokens.txt $d/
          mv -v scripts/nemo/GigaAM/*.wav $d/test_wavs/
          mv -v scripts/nemo/GigaAM/run-ctc.sh $d/
          mv -v scripts/nemo/GigaAM/*-ctc.py $d/

          ls -lh scripts/nemo/GigaAM/

          ls -lh $d

          tar cjvf ${d}.tar.bz2 $d

      - name: Run Transducer
        shell: bash
        run: |
          pushd scripts/nemo/GigaAM
          ./run-rnnt.sh
          popd

          d=sherpa-onnx-nemo-transducer-giga-am-russian-2024-10-24
          mkdir $d
          mkdir $d/test_wavs

          mv -v scripts/nemo/GigaAM/encoder.int8.onnx $d/
          mv -v scripts/nemo/GigaAM/decoder.onnx $d/
          mv -v scripts/nemo/GigaAM/joiner.onnx $d/

          cp -v scripts/nemo/GigaAM/*.md $d/
          mv -v scripts/nemo/GigaAM/*.pdf $d/
          mv -v scripts/nemo/GigaAM/tokens.txt $d/
          mv -v scripts/nemo/GigaAM/*.wav $d/test_wavs/
          mv -v scripts/nemo/GigaAM/run-rnnt.sh $d/
          mv -v scripts/nemo/GigaAM/*-rnnt.py $d/

          ls -lh scripts/nemo/GigaAM/

          ls -lh $d

          tar cjvf ${d}.tar.bz2 $d

      - 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 to huggingface (Transducer)
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN }}
        uses: nick-fields/retry@v3
        with:
          max_attempts: 20
          timeout_seconds: 200
          shell: bash
          command: |
            git config --global user.email "csukuangfj@gmail.com"
            git config --global user.name "Fangjun Kuang"

            d=sherpa-onnx-nemo-transducer-giga-am-russian-2024-10-24/
            export GIT_LFS_SKIP_SMUDGE=1
            export GIT_CLONE_PROTECTION_ACTIVE=false
            git clone https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d huggingface
            mv -v $d/* ./huggingface
            cd huggingface
            git lfs track "*.onnx"
            git lfs track "*.wav"
            git status
            git add .
            git status
            git commit -m "add models"
            git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d main