| | |
| | | chars = string.ascii_letters + string.digits |
| | | if isinstance(data_in, str) and data_in.startswith('http'): # url |
| | | data_in = download_from_url(data_in) |
| | | pdb.set_trace() |
| | | |
| | | if isinstance(data_in, str) and os.path.exists(data_in): # wav_path; filelist: wav.scp, file.jsonl;text.txt; |
| | | _, file_extension = os.path.splitext(data_in) |
| | | file_extension = file_extension.lower() |
| | |
| | | tokenizer=tokenizer) |
| | | time2 = time.perf_counter() |
| | | meta_data["load_data"] = f"{time2 - time1:0.3f}" |
| | | pdb.set_trace() |
| | | audio_sample_list = sample_list[0] |
| | | ocr_sample_list = sample_list[1] |
| | | speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), |
| | |
| | | encoder_out, encoder_out_lens = self.encode(speech, speech_lengths) |
| | | if isinstance(encoder_out, tuple): |
| | | encoder_out = encoder_out[0] |
| | | |
| | | pdb.set_trace() |
| | | ocr_list_new = [[x + 1 if x != 0 else x for x in sublist] for sublist in ocr_sample_list] |
| | | ocr = torch.tensor(ocr_list_new).to(device=kwargs["device"]) |
| | | ocr_lengths = ocr.new_full([1], dtype=torch.long, fill_value=ocr.size(1)).to(device=kwargs["device"]) |
| | |
| | | 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) |
| | | pdb.set_trace() |
| | | |
| | | 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) |
| | |
| | | else: |
| | | pass |
| | | # print(f"unsupport data type: {data_or_path_or_list}, return raw data") |
| | | pdb.set_trace() |
| | | |
| | | if audio_fs != fs and data_type != "text": |
| | | resampler = torchaudio.transforms.Resample(audio_fs, fs) |
| | | data_or_path_or_list = resampler(data_or_path_or_list[None, :])[0, :] |