Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add

游雁

2023-09-13 33d3d2084403fd34b79c835d2f2fe04f6cd8f738

 funasr/datasets/large_datasets/dataset.py

@@ -202,14 +202,7 @@
    data_types = conf.get("data_types", "kaldi_ark,text")

    pre_hwfile = conf.get("pre_hwlist", None)
    pre_prob = conf.get("pre_prob", 0)  # unused yet

    hw_config = {"sample_rate": conf.get("sample_rate", 0.6),
                 "double_rate": conf.get("double_rate", 0.1),
                 "hotword_min_length": conf.get("hotword_min_length", 2),
                 "hotword_max_length": conf.get("hotword_max_length", 8),
                 "pre_prob": conf.get("pre_prob", 0.0)}

    # pre_prob = conf.get("pre_prob", 0)  # unused yet
    if pre_hwfile is not None:
        pre_hwlist = []
        with open(pre_hwfile, 'r') as fin:
@@ -217,6 +210,15 @@
                pre_hwlist.append(line.strip())
    else:
        pre_hwlist = None

    hw_config = {"sample_rate": conf.get("sample_rate", 0.6),
                 "double_rate": conf.get("double_rate", 0.1),
                 "hotword_min_length": conf.get("hotword_min_length", 2),
                 "hotword_max_length": conf.get("hotword_max_length", 8),
                 "pre_prob": conf.get("pre_prob", 0.0),
                 "pre_hwlist": pre_hwlist}

    

    dataset = AudioDataset(scp_lists, 
                           data_names, 
@@ -227,15 +229,15 @@
                           mode=mode, 
                           )

    filter_conf = conf.get('filter_conf', {})
    filter_fn = partial(filter, **filter_conf)
    dataset = FilterIterDataPipe(dataset, fn=filter_fn)

    if "text" in data_names:
        vocab = {'vocab': dict, 'seg_dict': seg_dict, 'punc_dict': punc_dict, 'bpe_tokenizer': bpe_tokenizer, 'hw_config': hw_config}
        tokenize_fn = partial(tokenize, **vocab)
        dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)

    filter_conf = conf.get('filter_conf', {})
    filter_fn = partial(filter, **filter_conf)
    dataset = FilterIterDataPipe(dataset, fn=filter_fn)

    if shuffle:
        buffer_conf = conf.get('shuffle_conf', {})
        buffer_size = buffer_conf['shuffle_size']