merge

游雁

2023-11-24 afae93b43dcd6f9061dec5934b6536981c7ef363

 funasr/datasets/dataset_jsonl.py

@@ -22,10 +22,12 @@

def extract_features(data, date_type: str="sound", frontend=None):
   if date_type == "sound":

      if isinstance(data, np.ndarray):
         data = torch.from_numpy(data).to(torch.float32)
      data_len = torch.tensor([data.shape[0]]).to(torch.int32)
      feat, feats_lens = frontend(data[None, :], data_len)

      feat = feat[0, :, :]
   else:
      feat, feats_lens = torch.from_numpy(data).to(torch.float32), torch.tensor([data.shape[0]]).to(torch.int32)
@@ -78,6 +80,7 @@

class AudioDataset(torch.utils.data.Dataset):
   def __init__(self, path, frontend=None, tokenizer=None, token_id_converter=None):

      super().__init__()
      self.indexed_dataset = IndexedDatasetJsonl(path)
      self.frontend = frontend.forward
@@ -85,6 +88,7 @@
      self.data_type = "sound"
      self.tokenizer = tokenizer
      self.token_id_converter = token_id_converter

      self.int_pad_value = -1
      self.float_pad_value = 0.0

@@ -97,6 +101,7 @@
   def __getitem__(self, index):
      item = self.indexed_dataset[index]
      # return item

      source = item["source"]
      data_src = load_audio(source, fs=self.fs)
      speech, speech_lengths = extract_features(data_src, self.data_type, self.frontend)
@@ -105,6 +110,7 @@
      ids = self.token_id_converter.tokens2ids(text)
      ids_lengths = len(ids)
      text, text_lengths = torch.tensor(ids, dtype=torch.int64), torch.tensor([ids_lengths], dtype=torch.int32)

      return {"speech": speech,
              "speech_lengths": speech_lengths,
              "text": text,
@@ -125,8 +131,10 @@

      for key, data_list in outputs.items():
         if data_list[0].dtype == torch.int64:

            pad_value = self.int_pad_value
         else:
            pad_value = self.float_pad_value
         outputs[key] = torch.nn.utils.rnn.pad_sequence(data_list, batch_first=True, padding_value=pad_value)
      return outputs
      return outputs