fixbug hotwords

游雁

2024-06-24 1596f6f414f6f41da66506debb1dff19fffeb3ec

 funasr/datasets/large_datasets/utils/filter.py

@@ -1,15 +1,27 @@
#!/usr/bin/env python


def filter(data,
           min_length=10,
           max_length=10000,
           min_token_length=0,
           max_token_length=200):
    assert "speech" in data
    assert "text" in data
def filter(
    data, speech_length_min=100, speech_length_max=15000, token_length_min=0, token_length_max=200
):
    assert "speech" in data or "text" in data

    num_frames = data["speech"].shape[0]
    num_tokens = len(data['text'])

    return min_length < num_frames < max_length and min_token_length < num_tokens < max_token_length
    if "speech" in data and "text" in data:
        if "sampling_rate" in data:
            speech_length = (data["speech"].shape[0] / data["sampling_rate"]) * 1000.0
        else:
            speech_length = data["speech"].shape[0]
        num_tokens = len(data["text"])
        return (
            speech_length_min < speech_length < speech_length_max
            and token_length_min < num_tokens < token_length_max
        )
    elif "speech" in data:
        if "sampling_rate" in data:
            speech_length = (data["speech"].shape[0] / data["sampling_rate"]) * 1000.0
        else:
            speech_length = data["speech"].shape[0]
        return speech_length_min < speech_length < speech_length_max
    else:
        num_tokens = len(data["text"])
        return token_length_min < num_tokens < token_length_max