export model

游雁

2023-02-14 1d4ab65c8bfebaecbcb0eec0064bae9a321cad75

 funasr/datasets/iterable_dataset.py

@@ -11,14 +11,16 @@

import kaldiio
import numpy as np
import soundfile
import torch
import torchaudio
from torch.utils.data.dataset import IterableDataset
from typeguard import check_argument_types
import os.path

from funasr.datasets.dataset import ESPnetDataset


SUPPORT_AUDIO_TYPE_SETS = ['flac', 'mp3', 'ogg', 'opus', 'wav', 'pcm']

def load_kaldi(input):
    retval = kaldiio.load_mat(input)
@@ -58,9 +60,14 @@
    array = np.frombuffer((middle_data.astype(dtype) - offset) / abs_max, dtype=np.float32)
    return array

def load_pcm(input):
    with open(input,"rb") as f:
        bytes = f.read()
    return load_bytes(bytes)

DATA_TYPES = {
    "sound": lambda x: soundfile.read(x)[0],
    "sound": lambda x: torchaudio.load(x)[0][0].numpy(),
    "pcm": load_pcm,
    "kaldi_ark": load_kaldi,
    "bytes": load_bytes,
    "waveform": lambda x: x,
@@ -98,6 +105,7 @@
                [str, Dict[str, np.ndarray]], Dict[str, np.ndarray]
            ] = None,
            float_dtype: str = "float32",
            fs: dict = None,
            int_dtype: str = "long",
            key_file: str = None,
    ):
@@ -113,6 +121,7 @@
        self.float_dtype = float_dtype
        self.int_dtype = int_dtype
        self.key_file = key_file
        self.fs = fs

        self.debug_info = {}
        non_iterable_list = []
@@ -165,64 +174,94 @@
    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]
            uid = 'utt_id'
            name = self.path_name_type_list[0][1]
            _type = self.path_name_type_list[0][2]
            func = DATA_TYPES[_type]
            array = func(value)
            data[name] = array
            for i in range(linenum):
                value = self.path_name_type_list[i][0]
                uid = 'utt_id'
                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" 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:
                        array = torch.from_numpy(array)
                        array = array.unsqueeze(0)
                        array = torchaudio.transforms.Resample(orig_freq=audio_fs,
                                                       new_freq=model_fs)(array)
                        array = array.squeeze(0).numpy()
                data[name] = array

            if self.preprocess is not None:
                data = self.preprocess(uid, data)
            for name in data:
                count += 1
                value = data[name]
                if not isinstance(value, np.ndarray):
                    raise RuntimeError(
                        f'All values must be converted to np.ndarray object '
                        f'by preprocessing, but "{name}" is still {type(value)}.')
                # Cast to desired type
                if value.dtype.kind == 'f':
                    value = value.astype(self.float_dtype)
                elif value.dtype.kind == 'i':
                    value = value.astype(self.int_dtype)
                else:
                    raise NotImplementedError(
                        f'Not supported dtype: {value.dtype}')
                data[name] = value
                if self.preprocess is not None:
                    data = self.preprocess(uid, data)
                for name in data:
                    count += 1
                    value = data[name]
                    if not isinstance(value, np.ndarray):
                        raise RuntimeError(
                            f'All values must be converted to np.ndarray object '
                            f'by preprocessing, but "{name}" is still {type(value)}.')
                    # Cast to desired type
                    if value.dtype.kind == 'f':
                        value = value.astype(self.float_dtype)
                    elif value.dtype.kind == 'i':
                        value = value.astype(self.int_dtype)
                    else:
                        raise NotImplementedError(
                            f'Not supported dtype: {value.dtype}')
                    data[name] = value

            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]
            func = DATA_TYPES[_type]
            array = func(value)
            data[name] = array
            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()
                    if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
                        raise NotImplementedError(
                            f'Not supported audio type: {audio_type}')
                    if audio_type == "pcm":
                        _type = "pcm"

            if self.preprocess is not None:
                data = self.preprocess(uid, data)
            for name in data:
                count += 1
                value = data[name]
                if not isinstance(value, np.ndarray):
                    raise RuntimeError(
                        f'All values must be converted to np.ndarray object '
                        f'by preprocessing, but "{name}" is still {type(value)}.')
                # Cast to desired type
                if value.dtype.kind == 'f':
                    value = value.astype(self.float_dtype)
                elif value.dtype.kind == 'i':
                    value = value.astype(self.int_dtype)
                else:
                    raise NotImplementedError(
                        f'Not supported dtype: {value.dtype}')
                data[name] = value
                func = DATA_TYPES[_type]
                array = func(value)
                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:
                        array = torch.from_numpy(array)
                        array = array.unsqueeze(0)
                        array = torchaudio.transforms.Resample(orig_freq=audio_fs,
                                                               new_freq=model_fs)(array)
                        array = array.squeeze(0).numpy()
                data[name] = array

                if self.preprocess is not None:
                    data = self.preprocess(uid, data)
                for name in data:
                    count += 1
                    value = data[name]
                    if not isinstance(value, np.ndarray):
                        raise RuntimeError(
                            f'All values must be converted to np.ndarray object '
                            f'by preprocessing, but "{name}" is still {type(value)}.')
                    # Cast to desired type
                    if value.dtype.kind == 'f':
                        value = value.astype(self.float_dtype)
                    elif value.dtype.kind == 'i':
                        value = value.astype(self.int_dtype)
                    else:
                        raise NotImplementedError(
                            f'Not supported dtype: {value.dtype}')
                    data[name] = value

            yield uid, data

@@ -286,9 +325,25 @@
                data = {}
                # 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()
                        if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
                            raise NotImplementedError(
                                f'Not supported audio type: {audio_type}')
                        if audio_type == "pcm":
                            _type = "pcm"
                    func = DATA_TYPES[_type]
                    # Load entry
                    array = func(value)
                    if self.fs is not None and name == "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:
                            array = torch.from_numpy(array)
                            array = array.unsqueeze(0)
                            array = torchaudio.transforms.Resample(orig_freq=audio_fs,
                                                                   new_freq=model_fs)(array)
                            array = array.squeeze(0).numpy()
                    data[name] = array
                if self.non_iterable_dataset is not None:
                    # 2.b. Load data from non-iterable dataset