Refactor exporting NeMo models (#2362)
Refactors and extends model export support to include new NeMo Parakeet TDT int8 variants for English and Japanese, updating the Kotlin API, export scripts, test runners, and CI workflows. - Added support for two new int8 model types in OfflineRecognizer.kt. - Enhanced Python export scripts to perform dynamic quantization and metadata injection. - Updated shell scripts and GitHub workflows to package, test, and publish int8 model artifacts.
This commit is contained in:
@@ -54,13 +54,18 @@ jobs:
|
||||
curl -SL -O https://hf-mirror.com/csukuangfj/sherpa-onnx-nemo-ctc-en-conformer-small/resolve/main/test_wavs/trans.txt
|
||||
popd
|
||||
|
||||
cp -av test_wavs ./sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-80ms
|
||||
cp -av test_wavs ./sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-480ms
|
||||
cp -av test_wavs ./sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-1040ms
|
||||
|
||||
tar cjvf sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-80ms.tar.bz2 sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-80ms
|
||||
tar cjvf sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-480ms.tar.bz2 sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-480ms
|
||||
tar cjvf sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-1040ms.tar.bz2 sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-1040ms
|
||||
names=(
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-80ms
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-480ms
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-1040ms
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-80ms-int8
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-480ms-int8
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-1040ms-int8
|
||||
)
|
||||
for d in ${names[@]}; do
|
||||
cp -av test_wavs $d/
|
||||
tar cjvf $d.tar.bz2 $d
|
||||
done
|
||||
|
||||
- name: Release
|
||||
uses: svenstaro/upload-release-action@v2
|
||||
@@ -71,3 +76,41 @@ jobs:
|
||||
repo_name: k2-fsa/sherpa-onnx
|
||||
repo_token: ${{ secrets.UPLOAD_GH_SHERPA_ONNX_TOKEN }}
|
||||
tag: asr-models
|
||||
|
||||
- name: Publish to huggingface
|
||||
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"
|
||||
|
||||
models=(
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-80ms
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-480ms
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-1040ms
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-80ms-int8
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-480ms-int8
|
||||
sherpa-onnx-nemo-streaming-fast-conformer-ctc-en-1040ms-int8
|
||||
)
|
||||
|
||||
for m in ${models[@]}; do
|
||||
rm -rf huggingface
|
||||
export GIT_LFS_SKIP_SMUDGE=1
|
||||
export GIT_CLONE_PROTECTION_ACTIVE=false
|
||||
git clone https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$m huggingface
|
||||
cp -av $m/* huggingface
|
||||
cd huggingface
|
||||
git lfs track "*.onnx"
|
||||
git lfs track "*.wav"
|
||||
git status
|
||||
git add .
|
||||
git status
|
||||
git commit -m "first commit"
|
||||
git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$m main
|
||||
cd ..
|
||||
done
|
||||
|
||||
Reference in New Issue
Block a user