FunASR/funasr/export
2023-02-25 18:27:31 +08:00
..
models onnx 2023-02-25 18:27:31 +08:00
utils export model 2023-02-07 17:45:59 +08:00
__init__.py export model 2023-02-07 15:19:18 +08:00
export_model.py onnx 2023-02-25 18:27:31 +08:00
README.md readme 2023-02-16 12:50:43 +08:00
test_onnx.py export model test 2023-02-07 22:57:08 +08:00
test_torchscripts.py export model test 2023-02-07 22:57:08 +08:00

Environments

funasr 0.1.7
python 3.7
torch 1.11.0
modelscope 1.2.0

Install modelscope and funasr

The installation is the same as funasr

Export model

Tips: torch 1.11.0 is required.

python -m funasr.export.export_model [model_name] [export_dir] [onnx]

model_name: the model is to export. It could be the models from modelscope, or local finetuned model(named: model.pb). export_dir: the dir where the onnx is export. onnx: true, export onnx format model; false, export torchscripts format model.

For example

Export onnx format model

Export model from modelscope

python -m funasr.export.export_model 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" true

Export model from local path, the model'name must be model.pb.

python -m funasr.export.export_model '/mnt/workspace/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" true

Export torchscripts format model

Export model from modelscope

python -m funasr.export.export_model 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" false

Export model from local path, the model'name must be model.pb.

python -m funasr.export.export_model '/mnt/workspace/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" false