Merge pull request #94 from alibaba-damo-academy/gzf

zhifu gao

2023-02-10 41e4b59033cc0d627b2e244f0e2d602a43d91126

 funasr/export/export_model.py

@@ -1,3 +1,4 @@
import json
from typing import Union, Dict
from pathlib import Path
from typeguard import check_argument_types
@@ -8,14 +9,15 @@

from funasr.bin.asr_inference_paraformer import Speech2Text
from funasr.export.models import get_model


import numpy as np
import random

class ASRModelExportParaformer:
    def __init__(self, cache_dir: Union[Path, str] = None, onnx: bool = True):
        assert check_argument_types()
        self.set_all_random_seed(0)
        if cache_dir is None:
            cache_dir = Path.home() / "cache" / "export"
            cache_dir = Path.home() / ".cache" / "export"

        self.cache_dir = Path(cache_dir)
        self.export_config = dict(
@@ -24,8 +26,9 @@
        )
        logging.info("output dir: {}".format(self.cache_dir))
        self.onnx = onnx
        

    def export(
    def _export(
        self,
        model: Speech2Text,
        tag_name: str = None,
@@ -60,38 +63,38 @@
        model_script = torch.jit.trace(model, dummy_input)
        model_script.save(os.path.join(path, f'{model.model_name}.torchscripts'))

    def export_from_modelscope(
        self,
        tag_name: str = 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
    ):
    def set_all_random_seed(self, seed: int):
        random.seed(seed)
        np.random.seed(seed)
        torch.random.manual_seed(seed)
    def export(self,
               tag_name: str = 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
               mode: str = 'paraformer',
               ):
        
        from funasr.tasks.asr import ASRTaskParaformer as ASRTask
        from modelscope.hub.snapshot_download import snapshot_download

        model_dir = snapshot_download(tag_name, cache_dir=self.cache_dir)
        asr_train_config = os.path.join(model_dir, 'config.yaml')
        asr_model_file = os.path.join(model_dir, 'model.pb')
        cmvn_file = os.path.join(model_dir, 'am.mvn')
        model, asr_train_args = ASRTask.build_model_from_file(
            asr_train_config, asr_model_file, cmvn_file, 'cpu'
        )
        self.export(model, tag_name)

    def export_from_local(
        self,
        tag_name: str = '/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
    ):
    
        from funasr.tasks.asr import ASRTaskParaformer as ASRTask
    
        model_dir = tag_name
        if model_dir.startswith('damo/'):
            from modelscope.hub.snapshot_download import snapshot_download
            model_dir = snapshot_download(model_dir, cache_dir=self.cache_dir)
        asr_train_config = os.path.join(model_dir, 'config.yaml')
        asr_model_file = os.path.join(model_dir, 'model.pb')
        cmvn_file = os.path.join(model_dir, 'am.mvn')
        json_file = os.path.join(model_dir, 'configuration.json')
        if mode is None:
            import json
            with open(json_file, 'r') as f:
                config_data = json.load(f)
                mode = config_data['model']['model_config']['mode']
        if mode == 'paraformer':
            from funasr.tasks.asr import ASRTaskParaformer as ASRTask
        elif mode == 'uniasr':
            from funasr.tasks.asr import ASRTaskUniASR as ASRTask
            
        model, asr_train_args = ASRTask.build_model_from_file(
            asr_train_config, asr_model_file, cmvn_file, 'cpu'
        )
        self.export(model, tag_name)
        self._export(model, tag_name)
            

    def _export_onnx(self, model, verbose, path, enc_size=None):
        if enc_size:
@@ -116,5 +119,5 @@
if __name__ == '__main__':
    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.export_from_local('/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
    export_model.export('damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
    # export_model.export('/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')