update funasr-onnx-offline

雾聪

2023-06-02 fae856e23d45fd27d5fd55fd036e8e3fc7b24915

 funasr/build_utils/build_asr_model.py

@@ -23,7 +23,7 @@
from funasr.models.joint_net.joint_network import JointNetwork
from funasr.models.e2e_asr import ASRModel
from funasr.models.e2e_asr_mfcca import MFCCA
from funasr.models.e2e_asr_paraformer import Paraformer, ParaformerBert, BiCifParaformer, ContextualParaformer
from funasr.models.e2e_asr_paraformer import Paraformer, ParaformerOnline, ParaformerBert, BiCifParaformer, ContextualParaformer
from funasr.models.e2e_tp import TimestampPredictor
from funasr.models.e2e_uni_asr import UniASR
from funasr.models.e2e_asr_transducer import TransducerModel, UnifiedTransducerModel
@@ -82,11 +82,14 @@
        asr=ASRModel,
        uniasr=UniASR,
        paraformer=Paraformer,
        paraformer_online=ParaformerOnline,
        paraformer_bert=ParaformerBert,
        bicif_paraformer=BiCifParaformer,
        contextual_paraformer=ContextualParaformer,
        mfcca=MFCCA,
        timestamp_prediction=TimestampPredictor,
        rnnt=TransducerModel,
        rnnt_unified=UnifiedTransducerModel,
    ),
    default="asr",
)
@@ -291,7 +294,7 @@
            token_list=token_list,
            **args.model_conf,
        )
    elif args.model in ["paraformer", "paraformer_bert", "bicif_paraformer", "contextual_paraformer"]:
    elif args.model in ["paraformer", "paraformer_online", "paraformer_bert", "bicif_paraformer", "contextual_paraformer"]:
        # predictor
        predictor_class = predictor_choices.get_class(args.predictor)
        predictor = predictor_class(**args.predictor_conf)
@@ -367,7 +370,7 @@
            token_list=token_list,
            **args.model_conf,
        )
    elif args.model == "rnnt":
    elif args.model == "rnnt" or args.model == "rnnt_unified":
        # 5. Decoder
        encoder_output_size = encoder.output_size()

@@ -396,34 +399,21 @@
            **args.joint_network_conf,
        )

        model_class = model_choices.get_class(args.model)
        # 7. Build model
        if hasattr(encoder, 'unified_model_training') and encoder.unified_model_training:
            model = UnifiedTransducerModel(
                vocab_size=vocab_size,
                token_list=token_list,
                frontend=frontend,
                specaug=specaug,
                normalize=normalize,
                encoder=encoder,
                decoder=decoder,
                att_decoder=att_decoder,
                joint_network=joint_network,
                **args.model_conf,
            )
        model = model_class(
            vocab_size=vocab_size,
            token_list=token_list,
            frontend=frontend,
            specaug=specaug,
            normalize=normalize,
            encoder=encoder,
            decoder=decoder,
            att_decoder=att_decoder,
            joint_network=joint_network,
            **args.model_conf,
        )

        else:
            model = TransducerModel(
                vocab_size=vocab_size,
                token_list=token_list,
                frontend=frontend,
                specaug=specaug,
                normalize=normalize,
                encoder=encoder,
                decoder=decoder,
                att_decoder=att_decoder,
                joint_network=joint_network,
                **args.model_conf,
            )
    else:
        raise NotImplementedError("Not supported model: {}".format(args.model))