first commit (#1411)

.github/scripts/multi-zh-hans.sh

@@ -0,0 +1,88 @@
+#!/usr/bin/env bash
+
+set -ex
+
+log() {
+  # This function is from espnet
+  local fname=${BASH_SOURCE[1]##*/}
+  echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+
+log "pwd: $PWD"
+
+cd egs/multi_zh-hans/ASR
+
+repo_url=https://huggingface.co/zrjin/icefall-asr-multi-zh-hans-zipformer-ctc-streaming-2023-11-05
+log "Downloading pre-trained model from $repo_url"
+GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
+repo=$(basename $repo_url)
+
+pushd $repo
+cd exp/
+git lfs pull --include pretrained.pt
+rm -fv epoch-20.pt
+rm -fv *.onnx
+ln -s pretrained.pt epoch-20.pt
+cd ../data/lang_bpe_2000
+git lfs pull --include L.pt L_disambig.pt Linv.pt bpe.model
+popd
+
+log "----------------------------------------"
+log "Export streaming ONNX transducer models "
+log "----------------------------------------"
+
+./zipformer/export-onnx-streaming.py \
+  --exp-dir $repo/exp \
+  --tokens $repo/data/lang_bpe_2000/tokens.txt \
+  --causal 1 \
+  --avg 1 \
+  --epoch 20 \
+  --use-averaged-model 0 \
+  --chunk-size 16 \
+  --left-context-frames 128 \
+  --use-ctc 0
+
+ls -lh $repo/exp
+
+log "------------------------------------------------------------"
+log "Test export streaming ONNX transducer models (Python code)  "
+log "------------------------------------------------------------"
+
+log "test fp32"
+./zipformer/onnx_pretrained-streaming.py \
+  --encoder-model-filename $repo/exp/encoder-epoch-20-avg-1-chunk-16-left-128.onnx \
+  --decoder-model-filename $repo/exp/decoder-epoch-20-avg-1-chunk-16-left-128.onnx \
+  --joiner-model-filename $repo/exp/joiner-epoch-20-avg-1-chunk-16-left-128.onnx \
+  --tokens $repo/data/lang_bpe_2000/tokens.txt \
+  $repo/test_wavs/DEV_T0000000000.wav
+
+log "test int8"
+./zipformer/onnx_pretrained-streaming.py \
+  --encoder-model-filename $repo/exp/encoder-epoch-20-avg-1-chunk-16-left-128.int8.onnx \
+  --decoder-model-filename $repo/exp/decoder-epoch-20-avg-1-chunk-16-left-128.onnx \
+  --joiner-model-filename $repo/exp/joiner-epoch-20-avg-1-chunk-16-left-128.int8.onnx \
+  --tokens $repo/data/lang_bpe_2000/tokens.txt \
+  $repo/test_wavs/DEV_T0000000000.wav
+
+log "Upload models to huggingface"
+git config --global user.name "k2-fsa"
+git config --global user.email "[email protected]"
+
+url=https://huggingface.co/k2-fsa/sherpa-onnx-streaming-zipformer-multi-zh-hans-2023-12-12
+GIT_LFS_SKIP_SMUDGE=1 git clone $url
+dst=$(basename $url)
+cp -v $repo/exp/*.onnx $dst
+cp -v $repo/data/lang_bpe_2000/tokens.txt $dst
+mkdir -p $dst/test_wavs
+cp -v $repo/test_wavs/*.wav $dst/test_wavs
+cd $dst
+git lfs track "*.onnx"
+git add .
+git commit -m "upload model" && git push https://k2-fsa:${HF_TOKEN}@huggingface.co/k2-fsa/$dst main || true
+
+log "Upload models to https://github.com/k2-fsa/sherpa-onnx"
+rm -rf .git
+rm -fv .gitattributes
+cd ..
+tar cjfv $dst.tar.bz2 $dst
+mv -v $dst.tar.bz2 ../../../

.github/workflows/multi-zh-hans.yml

@@ -0,0 +1,84 @@
+name: run-multi-zh-hans
+
+on:
+  push:
+    branches:
+      - master
+      - upload-ctc-model
+
+  pull_request:
+    branches:
+      - master
+
+  workflow_dispatch:
+
+concurrency:
+  group: run-multi-zh-hans-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: write
+
+jobs:
+  multi-zh-hans:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        python-version: [3.8]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+          cache-dependency-path: '**/requirements-ci.txt'
+
+      - name: Install Python dependencies
+        run: |
+          grep -v '^#' ./requirements-ci.txt  | xargs -n 1 -L 1 pip install
+          pip uninstall -y protobuf
+          pip install --no-binary protobuf protobuf==3.20.*
+
+      - name: Cache kaldifeat
+        id: my-cache
+        uses: actions/cache@v2
+        with:
+          path: |
+            ~/tmp/kaldifeat
+          key: cache-tmp-${{ matrix.python-version }}-2023-05-22
+
+      - name: Install kaldifeat
+        if: steps.my-cache.outputs.cache-hit != 'true'
+        shell: bash
+        run: |
+          .github/scripts/install-kaldifeat.sh
+
+      - name: export-model
+        shell: bash
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          sudo apt-get -qq install git-lfs tree
+          export PYTHONPATH=$PWD:$PYTHONPATH
+          export PYTHONPATH=~/tmp/kaldifeat/kaldifeat/python:$PYTHONPATH
+          export PYTHONPATH=~/tmp/kaldifeat/build/lib:$PYTHONPATH
+
+          .github/scripts/multi-zh-hans.sh
+          ls -lh
+
+      - name: upload model to https://github.com/k2-fsa/sherpa-onnx
+        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

egs/librispeech/ASR/zipformer/export-onnx-streaming.py

@@ -614,7 +614,9 @@ def main():
                 )
             logging.info(f"averaging {filenames}")
             model.to(device)
-            model.load_state_dict(average_checkpoints(filenames, device=device))
+            model.load_state_dict(
+                average_checkpoints(filenames, device=device), strict=False
+            )
         elif params.avg == 1:
             load_checkpoint(f"{params.exp_dir}/epoch-{params.epoch}.pt", model)
         else:
@@ -625,7 +627,9 @@ def main():
                     filenames.append(f"{params.exp_dir}/epoch-{i}.pt")
             logging.info(f"averaging {filenames}")
             model.to(device)
-            model.load_state_dict(average_checkpoints(filenames, device=device))
+            model.load_state_dict(
+                average_checkpoints(filenames, device=device), strict=False
+            )
     else:
         if params.iter > 0:
             filenames = find_checkpoints(params.exp_dir, iteration=-params.iter)[
@@ -653,7 +657,8 @@ def main():
                     filename_start=filename_start,
                     filename_end=filename_end,
                     device=device,
-                )
+                ),
+                strict=False,
             )
         else:
             assert params.avg > 0, params.avg
@@ -671,7 +676,8 @@ def main():
                     filename_start=filename_start,
                     filename_end=filename_end,
                     device=device,
-                )
+                ),
+                strict=False,
             )
 
     model.to("cpu")