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
567ecebbaf
FunASR/funasr/export/README.md
游雁 567ecebbaf export model test
2023-02-07 23:01:35 +08:00

1.5 KiB
Raw Blame History

environment: ubuntu20.04-py37-torch1.11.0-tf1.15.5-1.2.0

install modelscope and funasr

The install is the same as funasr

export onnx format model

Export model modelscope

from funasr.export.export_model import ASRModelExportParaformer

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

Export model from local path

from funasr.export.export_model import ASRModelExportParaformer

output_dir = "../export"
export_model = ASRModelExportParaformer(cache_dir=output_dir, onnx=True)
export_model.export_from_local('/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')

export torchscripts format model

Export model modelscope

from funasr.export.export_model import ASRModelExportParaformer

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

Export model from local path

from funasr.export.export_model import ASRModelExportParaformer

output_dir = "../export"
export_model = ASRModelExportParaformer(cache_dir=output_dir, onnx=False)
export_model.export_from_local('/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')