| | |
|---|
| | | import numpy as np |
|---|
| | | import torch |
|---|
| | | import torchaudio |
|---|
| | | import soundfile |
|---|
| | | # import librosa |
|---|
| | | import librosa |
|---|
| | | from torch.utils.data.dataset import IterableDataset |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | import os.path |
|---|
| | | |
|---|
| | | from funasr.datasets.dataset import ESPnetDataset |
|---|
| | |
|---|
| | | try: |
|---|
| | | return torchaudio.load(input)[0].numpy() |
|---|
| | | except: |
|---|
| | | return np.expand_dims(soundfile.read(input)[0], axis=0) |
|---|
| | | # waveform, _ = librosa.load(input, dtype='float32') |
|---|
| | | waveform, _ = librosa.load(input, dtype='float32') |
|---|
| | | if waveform.ndim == 2: |
|---|
| | | waveform = waveform[:, 0] |
|---|
| | | return np.expand_dims(waveform, axis=0) |
|---|
| | | |
|---|
| | | DATA_TYPES = { |
|---|
| | | "sound": load_wav, |
|---|
| | |
|---|
| | | int_dtype: str = "long", |
|---|
| | | key_file: str = None, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | if len(path_name_type_list) == 0: |
|---|
| | | raise ValueError( |
|---|
| | | '1 or more elements are required for "path_name_type_list"' |
|---|
