Merge branch 'dev_gzf' of github.com:alibaba-damo-academy/FunASR into dev_g...

游雁

2023-02-16 544b798b32819fe2ffed1fccb44e8c2620449a53

 funasr/datasets/iterable_dataset.py

@@ -174,14 +174,16 @@
    def __iter__(self) -> Iterator[Tuple[Union[str, int], Dict[str, np.ndarray]]]:
        count = 0
        if len(self.path_name_type_list) != 0 and (self.path_name_type_list[0][2] == "bytes" or self.path_name_type_list[0][2] == "waveform"):
            linenum = len(self.path_name_type_list)
            data = {}
            value = self.path_name_type_list[0][0]
            for i in range(linenum):
                value = self.path_name_type_list[i][0]
            uid = 'utt_id'
            name = self.path_name_type_list[0][1]
            _type = self.path_name_type_list[0][2]
                name = self.path_name_type_list[i][1]
                _type = self.path_name_type_list[i][2]
            func = DATA_TYPES[_type]
            array = func(value)
            if self.fs is not None and name == "speech":
                if self.fs is not None and (name == "speech" or name == "ref_speech"):
                audio_fs = self.fs["audio_fs"]
                model_fs = self.fs["model_fs"]
                if audio_fs is not None and model_fs is not None:
@@ -214,13 +216,15 @@
            yield uid, data

        elif len(self.path_name_type_list) != 0 and self.path_name_type_list[0][2] == "sound" and not self.path_name_type_list[0][0].lower().endswith(".scp"):
            linenum = len(self.path_name_type_list)
            data = {}
            value = self.path_name_type_list[0][0]
            uid = os.path.basename(self.path_name_type_list[0][0]).split(".")[0]
            name = self.path_name_type_list[0][1]
            _type = self.path_name_type_list[0][2]
            for i in range(linenum):
                value = self.path_name_type_list[i][0]
                uid = os.path.basename(self.path_name_type_list[i][0]).split(".")[0]
                name = self.path_name_type_list[i][1]
                _type = self.path_name_type_list[i][2]
            if _type == "sound":
                audio_type = os.path.basename(value).split(".")[1].lower()
                    audio_type = os.path.basename(value).split(".")[-1].lower()
                if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
                    raise NotImplementedError(
                        f'Not supported audio type: {audio_type}')
@@ -229,7 +233,7 @@

            func = DATA_TYPES[_type]
            array = func(value)
            if self.fs is not None and name == "speech":
                if self.fs is not None and (name == "speech" or name == "ref_speech"):
                audio_fs = self.fs["audio_fs"]
                model_fs = self.fs["model_fs"]
                if audio_fs is not None and model_fs is not None:
@@ -322,7 +326,7 @@
                # 2.a. Load data streamingly
                for value, (path, name, _type) in zip(values, self.path_name_type_list):
                    if _type == "sound":
                        audio_type = os.path.basename(value).split(".")[1].lower()
                        audio_type = os.path.basename(value).split(".")[-1].lower()
                        if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
                            raise NotImplementedError(
                                f'Not supported audio type: {audio_type}')