feat: add speech-brain-asr-whisper-large-v2-commonvoice-fa #87
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# yaml-language-server: $schema=https://json.schemastore.org/github-workflow.json | |
name: Run ASR model benchmark | |
on: | |
workflow_dispatch: | |
pull_request: | |
push: | |
branches: | |
- next | |
jobs: | |
benchmark: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
include: | |
- path: wav2vec2-large-xlsr-persian-v3 | |
- path: nemo | |
- path: whisper-large-v3 | |
- path: speech-brain-asr-whisper-large-v2-commonvoice-fa | |
steps: | |
- name: Checkout repository | |
uses: actions/checkout@v4 | |
- name: Set up Python | |
uses: actions/setup-python@v5 | |
with: | |
python-version: "3.11" | |
- name: Cache pip | |
uses: actions/cache@v4 | |
with: | |
path: ~/.cache/pip | |
key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}-${{ hashFiles('**/setup.py') }} | |
restore-keys: | | |
${{ runner.os }}-pip- | |
- name: Install ffmpeg | |
run: | | |
sudo apt-get install -y ffmpeg | |
- name: Install dependencies | |
run: pip3 install -r ${{ matrix.path }}/requirements.txt | |
- name: Run Python script to transcript and generate report | |
id: benchmark_run | |
run: | | |
cd ${{ matrix.path }} | |
python main.py | |
- name: Generate comment | |
run: | | |
cd ${{ matrix.path }} | |
report=$(cat result.json | jq -r '[.transcription, .werBeforeNormalization, .normalizedTranscription, .werAfterNormalization] | @csv') | |
echo "## ASR Benchmark Report for ${{ matrix.path }}" >> $GITHUB_STEP_SUMMARY | |
echo "| Transcription | WER Before Normalization | Normalized Transcription | WER After Normalization |" >> $GITHUB_STEP_SUMMARY | |
echo "|---|---|---|---|" >> $GITHUB_STEP_SUMMARY | |
echo "$report" | awk -F, '{print "| " $1 " | " $2 " | " $3 " | " $4 " |"}' >> $GITHUB_STEP_SUMMARY |