Merge pull request #687 from alibaba-damo-academy/dev_lhn

hnluo

2023-06-29 c2dee5e3c29eba79e591d9e9caebaef15ea4e56b

 funasr/export/export_model.py

@@ -19,28 +19,30 @@
        self,
        cache_dir: Union[Path, str] = None,
        onnx: bool = True,
        device: str = "cpu",
        quant: bool = True,
        fallback_num: int = 0,
        audio_in: str = None,
        calib_num: int = 200,
        model_revision: str = None,
    ):
        assert check_argument_types()
        self.set_all_random_seed(0)
        if cache_dir is None:
            cache_dir = Path.home() / ".cache" / "export"

        self.cache_dir = Path(cache_dir)
        self.cache_dir = cache_dir
        self.export_config = dict(
            feats_dim=560,
            onnx=False,
        )
        print("output dir: {}".format(self.cache_dir))
        
        self.onnx = onnx
        self.device = device
        self.quant = quant
        self.fallback_num = fallback_num
        self.frontend = None
        self.audio_in = audio_in
        self.calib_num = calib_num
        self.model_revision = model_revision
        

    def _export(
@@ -50,7 +52,7 @@
        verbose: bool = False,
    ):

        export_dir = self.cache_dir / tag_name.replace(' ', '-')
        export_dir = self.cache_dir
        os.makedirs(export_dir, exist_ok=True)

        # export encoder1
@@ -112,6 +114,10 @@
        else:
            dummy_input = model.get_dummy_inputs()

        if self.device == 'cuda':
            model = model.cuda()
            dummy_input = tuple([i.cuda() for i in dummy_input])

        # model_script = torch.jit.script(model)
        model_script = torch.jit.trace(model, dummy_input)
        model_script.save(os.path.join(path, f'{model.model_name}.torchscripts'))
@@ -161,31 +167,58 @@
    
    def export(self,
               tag_name: str = 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
               mode: str = 'paraformer',
               mode: str = None,
               ):
        
        model_dir = tag_name
        if model_dir.startswith('damo/'):
        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')
            model_dir = snapshot_download(model_dir, cache_dir=self.cache_dir, revision=self.model_revision)
        self.cache_dir = model_dir

        if mode is None:
            import json
            json_file = os.path.join(model_dir, 'configuration.json')
            with open(json_file, 'r') as f:
                config_data = json.load(f)
                mode = config_data['model']['model_config']['mode']
                if config_data['task'] == "punctuation":
                    mode = config_data['model']['punc_model_config']['mode']
                else:
                    mode = config_data['model']['model_config']['mode']
        if mode.startswith('paraformer'):
            from funasr.tasks.asr import ASRTaskParaformer as ASRTask
        elif mode.startswith('uniasr'):
            from funasr.tasks.asr import ASRTaskUniASR as ASRTask
            config = os.path.join(model_dir, 'config.yaml')
            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(
                config, model_file, cmvn_file, 'cpu'
            )
            self.frontend = model.frontend
        elif mode.startswith('offline'):
            from funasr.tasks.vad import VADTask
            config = os.path.join(model_dir, 'vad.yaml')
            model_file = os.path.join(model_dir, 'vad.pb')
            cmvn_file = os.path.join(model_dir, 'vad.mvn')
            
        model, asr_train_args = ASRTask.build_model_from_file(
            asr_train_config, asr_model_file, cmvn_file, 'cpu'
        )
        self.frontend = model.frontend
            model, vad_infer_args = VADTask.build_model_from_file(
                config, model_file, cmvn_file=cmvn_file, device='cpu'
            )
            self.export_config["feats_dim"] = 400
            self.frontend = model.frontend
        elif mode.startswith('punc'):
            from funasr.tasks.punctuation import PunctuationTask as PUNCTask
            punc_train_config = os.path.join(model_dir, 'config.yaml')
            punc_model_file = os.path.join(model_dir, 'punc.pb')
            model, punc_train_args = PUNCTask.build_model_from_file(
                punc_train_config, punc_model_file, 'cpu'
            )
        elif mode.startswith('punc_VadRealtime'):
            from funasr.tasks.punctuation import PunctuationTask as PUNCTask
            punc_train_config = os.path.join(model_dir, 'config.yaml')
            punc_model_file = os.path.join(model_dir, 'punc.pb')
            model, punc_train_args = PUNCTask.build_model_from_file(
                punc_train_config, punc_model_file, 'cpu'
            )
        self._export(model, tag_name)
            

@@ -198,34 +231,35 @@
        # model_script = torch.jit.script(model)
        model_script = model #torch.jit.trace(model)
        model_path = os.path.join(path, f'{model.model_name}.onnx')

        torch.onnx.export(
            model_script,
            dummy_input,
            model_path,
            verbose=verbose,
            opset_version=14,
            input_names=model.get_input_names(),
            output_names=model.get_output_names(),
            dynamic_axes=model.get_dynamic_axes()
        )
        if not os.path.exists(model_path):
            torch.onnx.export(
                model_script,
                dummy_input,
                model_path,
                verbose=verbose,
                opset_version=14,
                input_names=model.get_input_names(),
                output_names=model.get_output_names(),
                dynamic_axes=model.get_dynamic_axes()
            )

        if self.quant:
            from onnxruntime.quantization import QuantType, quantize_dynamic
            import onnx
            quant_model_path = os.path.join(path, f'{model.model_name}_quant.onnx')
            onnx_model = onnx.load(model_path)
            nodes = [n.name for n in onnx_model.graph.node]
            nodes_to_exclude = [m for m in nodes if 'output' in m]
            quantize_dynamic(
                model_input=model_path,
                model_output=quant_model_path,
                op_types_to_quantize=['MatMul'],
                per_channel=True,
                reduce_range=False,
                weight_type=QuantType.QUInt8,
                nodes_to_exclude=nodes_to_exclude,
            )
            if not os.path.exists(quant_model_path):
                onnx_model = onnx.load(model_path)
                nodes = [n.name for n in onnx_model.graph.node]
                nodes_to_exclude = [m for m in nodes if 'output' in m]
                quantize_dynamic(
                    model_input=model_path,
                    model_output=quant_model_path,
                    op_types_to_quantize=['MatMul'],
                    per_channel=True,
                    reduce_range=False,
                    weight_type=QuantType.QUInt8,
                    nodes_to_exclude=nodes_to_exclude,
                )


if __name__ == '__main__':
@@ -234,18 +268,22 @@
    parser.add_argument('--model-name', type=str, required=True)
    parser.add_argument('--export-dir', type=str, required=True)
    parser.add_argument('--type', type=str, default='onnx', help='["onnx", "torch"]')
    parser.add_argument('--device', type=str, default='cpu', help='["cpu", "cuda"]')
    parser.add_argument('--quantize', type=str2bool, default=False, help='export quantized model')
    parser.add_argument('--fallback-num', type=int, default=0, help='amp fallback number')
    parser.add_argument('--audio_in', type=str, default=None, help='["wav", "wav.scp"]')
    parser.add_argument('--calib_num', type=int, default=200, help='calib max num')
    parser.add_argument('--model_revision', type=str, default=None, help='model_revision')
    args = parser.parse_args()

    export_model = ModelExport(
        cache_dir=args.export_dir,
        onnx=args.type == 'onnx',
        device=args.device,
        quant=args.quantize,
        fallback_num=args.fallback_num,
        audio_in=args.audio_in,
        calib_num=args.calib_num,
        model_revision=args.model_revision,
    )
    export_model.export(args.model_name)