train (#1521)

zhifu gao

2024-03-21 4482bbcbb912f699a4faecaafd65aa15aec64a51

 funasr/datasets/large_datasets/utils/tokenize.py

@@ -1,6 +1,7 @@
#!/usr/bin/env python
import re
import numpy as np
from funasr.datasets.large_datasets.utils.hotword_utils import sample_hotword

def forward_segment(text, seg_dict):
    word_list = []
@@ -17,38 +18,59 @@
    return word_list

def seg_tokenize(txt, seg_dict):
    pattern = re.compile(r'^[\u4E00-\u9FA50-9]+$')
    out_txt = ""
    pattern = re.compile(r"([\u4E00-\u9FA5A-Za-z0-9])")
    for word in txt:
        if pattern.match(word):
            if word in seg_dict:
                out_txt += seg_dict[word] + " "
        word = word.lower()
        if word in seg_dict:
            out_txt += seg_dict[word] + " "
        else:
            if pattern.match(word):
                for char in word:
                    if char in seg_dict:
                        out_txt += seg_dict[char] + " "
                    else:
                        out_txt += "<unk>" + " "
            else:
                out_txt += "<unk>" + " "
        else:
            continue
    return out_txt.strip().split()

def tokenize(data,
             vocab=None,
             seg_dict=None,
             punc_dict=None):
             punc_dict=None,
             bpe_tokenizer=None,
             hw_config=None):
    assert "text" in data
    assert isinstance(vocab, dict)
    text = data["text"]
    token = []
    vad = -2

    if bpe_tokenizer is not None:
        text = bpe_tokenizer.text2tokens(" ".join(text))
    if seg_dict is not None:
        assert isinstance(seg_dict, dict)
        txt = forward_segment("".join(text).lower(), seg_dict)
        text = seg_tokenize(txt, seg_dict)
        text = seg_tokenize(text, seg_dict)

    length = len(text)
    if 'hw_tag' in data:
        pre_index = None
        if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0:
            # enable preset hotword detect in sampling
            for hw in hw_config['pre_hwlist']:
                hw = " ".join(seg_tokenize(hw, seg_dict))
                _find = " ".join(text).find(hw)
                if _find != -1:
                    # _find = text[:_find].count(" ")  # bpe sometimes
                    pre_index = [_find, _find + max(hw.count(" "), 1)]
                    break
        hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
        data['hotword_indxs'] = hotword_indxs
        del data['hw_tag']
    for i in range(length):
        x = text[i]
        if i == length-1 and "punc" in data and text[i].startswith("vad:"):
            vad = x[-1][4:]
        if i == length-1 and "punc" in data and x.startswith("vad:"):
            vad = x[4:]
            if len(vad) == 0:
                vad = -1
            else: