From be7539ee4a51679eeff86f3a9323a237a31e2861 Mon Sep 17 00:00:00 2001 From: Fangjun Kuang Date: Tue, 29 Oct 2024 15:13:01 +0800 Subject: [PATCH] Fix CI for gigaspeech --- ...eech-pruned-transducer-stateless2-2022-05-12.sh | 14 +++++++++++--- .github/workflows/run-gigaspeech-2022-05-13.yml | 6 +++--- 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/.github/scripts/run-gigaspeech-pruned-transducer-stateless2-2022-05-12.sh b/.github/scripts/run-gigaspeech-pruned-transducer-stateless2-2022-05-12.sh index c9e798a68..8d98fca1e 100755 --- a/.github/scripts/run-gigaspeech-pruned-transducer-stateless2-2022-05-12.sh +++ b/.github/scripts/run-gigaspeech-pruned-transducer-stateless2-2022-05-12.sh @@ -19,7 +19,7 @@ repo=$(basename $repo_url) echo "GITHUB_EVENT_NAME: ${GITHUB_EVENT_NAME}" echo "GITHUB_EVENT_LABEL_NAME: ${GITHUB_EVENT_LABEL_NAME}" -if [[ x"${GITHUB_EVENT_NAME}" == x"schedule" || x"${GITHUB_EVENT_LABEL_NAME}" == x"run-decode" ]]; then +if [[ x"${GITHUB_EVENT_NAME}" == x"schedule" || x"${GITHUB_EVENT_NAME}" == x"workflow_dispatch" || x"${GITHUB_EVENT_LABEL_NAME}" == x"run-decode" ]]; then mkdir -p pruned_transducer_stateless2/exp ln -s $PWD/$repo/exp/pretrained-iter-3488000-avg-20.pt pruned_transducer_stateless2/exp/epoch-999.pt ln -s $PWD/$repo/data/lang_bpe_500 data/ @@ -29,8 +29,16 @@ if [[ x"${GITHUB_EVENT_NAME}" == x"schedule" || x"${GITHUB_EVENT_LABEL_NAME}" == ls -lh data/fbank ls -lh pruned_transducer_stateless2/exp - ln -sf data/fbank/cuts_DEV.jsonl.gz data/fbank/gigaspeech_cuts_DEV.jsonl.gz - ln -sf data/fbank/cuts_TEST.jsonl.gz data/fbank/gigaspeech_cuts_TEST.jsonl.gz + pushd data/fbank + curl -SL -O https://huggingface.co/csukuangfj/giga-dev-dataset-fbank/resolve/main/data/fbank/cuts_DEV.jsonl.gz + curl -SL -O https://huggingface.co/csukuangfj/giga-dev-dataset-fbank/resolve/main/data/fbank/cuts_TEST.jsonl.gz + curl -SL -O https://huggingface.co/csukuangfj/giga-dev-dataset-fbank/resolve/main/data/fbank/feats_DEV.lca + curl -SL -O https://huggingface.co/csukuangfj/giga-dev-dataset-fbank/resolve/main/data/fbank/feats_TEST.lca + + ln -sf cuts_DEV.jsonl.gz gigaspeech_cuts_DEV.jsonl.gz + ln -sf cuts_TEST.jsonl.gz gigaspeech_cuts_TEST.jsonl.gz + popd + log "Decoding dev and test" diff --git a/.github/workflows/run-gigaspeech-2022-05-13.yml b/.github/workflows/run-gigaspeech-2022-05-13.yml index 2c1d44fbf..9fd05d94a 100644 --- a/.github/workflows/run-gigaspeech-2022-05-13.yml +++ b/.github/workflows/run-gigaspeech-2022-05-13.yml @@ -41,7 +41,7 @@ concurrency: jobs: run_gigaspeech_2022_05_13: - if: github.event.label.name == 'ready' || github.event.label.name == 'run-decode' || github.event_name == 'push' || github.event_name == 'schedule' + if: github.event_name == 'workflow_dispatch' || github.event.label.name == 'ready' || github.event.label.name == 'run-decode' || github.event_name == 'push' || github.event_name == 'schedule' runs-on: ${{ matrix.os }} strategy: matrix: @@ -106,7 +106,7 @@ jobs: .github/scripts/run-gigaspeech-pruned-transducer-stateless2-2022-05-12.sh - name: Display decoding results for gigaspeech pruned_transducer_stateless2 - if: github.event_name == 'schedule' || github.event.label.name == 'run-decode' + if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' || github.event.label.name == 'run-decode' shell: bash run: | cd egs/gigaspeech/ASR/ @@ -122,7 +122,7 @@ jobs: - name: Upload decoding results for gigaspeech pruned_transducer_stateless2 uses: actions/upload-artifact@v4 - if: github.event_name == 'schedule' || github.event.label.name == 'run-decode' + if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' || github.event.label.name == 'run-decode' with: name: torch-${{ matrix.torch }}-python-${{ matrix.python-version }}-ubuntu-latest-cpu-gigaspeech-pruned_transducer_stateless2-2022-05-12 path: egs/gigaspeech/ASR/pruned_transducer_stateless2/exp/