speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
7114c13aa3
FunASR/funasr/export
History
游雁 7114c13aa3 export model
2023-02-11 23:54:42 +08:00
..
models exoprt model 2023-02-10 15:18:33 +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 export model 2023-02-11 23:54:42 +08:00
README.md exoprt model 2023-02-10 15:18:33 +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

README.md

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 onnx format model

Export model from modelscope

from funasr.export.export_model import ASRModelExportParaformer

output_dir = "../export"  # onnx/torchscripts model save path
export_model = ASRModelExportParaformer(cache_dir=output_dir, onnx=True)
export_model.export('damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')

Export model from local path

export_model.export('/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')

Export torchscripts format model

Export model from modelscope

from funasr.export.export_model import ASRModelExportParaformer

output_dir = "../export"  # onnx/torchscripts model save path
export_model = ASRModelExportParaformer(cache_dir=output_dir, onnx=False)
export_model.export('damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')

Export model from local path


export_model.export('/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')