This repository has been archived on 2025-08-26. You can view files and clone it, but cannot push or open issues or pull requests.
Files
enginex-mr_series-sherpa-onnx/scripts/nemo/parakeet-tdt_ctc-0.6b-ja/run-ctc.sh
Fangjun Kuang 6122a678f5 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.
2025-07-09 16:02:12 +08:00

35 lines
915 B
Bash
Executable File

#!/usr/bin/env bash
set -ex
python3 ./export-onnx-ctc.py
ls -lh *.onnx
mkdir -p test_wavs
pushd test_wavs
curl -SL -O https://huggingface.co/csukuangfj/reazonspeech-k2-v2-ja-en/resolve/main/test_wavs/transcripts.txt
curl -SL -O https://hf-mirror.com/csukuangfj/reazonspeech-k2-v2-ja-en/resolve/main/test_wavs/test_ja_1.wav
curl -SL -O https://hf-mirror.com/csukuangfj/reazonspeech-k2-v2-ja-en/resolve/main/test_wavs/test_ja_2.wav
popd
d=sherpa-onnx-nemo-parakeet-tdt_ctc-0.6b-ja-35000-int8
mkdir -p $d
mv -v model.int8.onnx $d/
cp -v tokens.txt $d/
cp -av test_wavs $d
ls -lh $d
d=sherpa-onnx-nemo-parakeet-tdt_ctc-0.6b-ja-35000-int8
python3 ./test-onnx-ctc-non-streaming.py \
--model $d/model.int8.onnx \
--tokens $d/tokens.txt \
--wav $d/test_wavs/test_ja_1.wav
python3 ./test-onnx-ctc-non-streaming.py \
--model $d/model.int8.onnx \
--tokens $d/tokens.txt \
--wav $d/test_wavs/test_ja_2.wav