| | |
|---|
| | | return [load_audio_text_image_video(audio, fs=fs, audio_fs=audio_fs, data_type=data_type, **kwargs) for audio in data_or_path_or_list] |
|---|
| | | if isinstance(data_or_path_or_list, str) and data_or_path_or_list.startswith('http'): # download url to local file |
|---|
| | | data_or_path_or_list = download_from_url(data_or_path_or_list) |
|---|
| | | |
|---|
| | | if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local file |
|---|
| | | if data_type is None or data_type == "sound": |
|---|
| | | data_or_path_or_list, audio_fs = torchaudio.load(data_or_path_or_list) |
|---|
| | | pdb.set_trace() |
|---|
| | | if kwargs.get("reduce_channels", True): |
|---|
| | | data_or_path_or_list = data_or_path_or_list.mean(0) |
|---|
| | | elif data_type == "text" and tokenizer is not None: |
|---|
| | |
|---|
| | | return array |
|---|
| | | |
|---|
| | | def extract_fbank(data, data_len = None, data_type: str="sound", frontend=None, **kwargs): |
|---|
| | | # import pdb; |
|---|
| | | # pdb.set_trace() |
|---|
| | | if isinstance(data, np.ndarray): |
|---|
| | | data = torch.from_numpy(data) |
|---|
| | | if len(data.shape) < 2: |
|---|
