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
979b0e96b0
FunASR/funasr/export/README.md
游雁 979b0e96b0 vad asr punc
2023-02-08 17:29:37 +08:00

1.7 KiB
Raw Blame History

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_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"  # onnx/torchscripts model save path
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 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_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"  # onnx/torchscripts model save path
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')