FunASR
FunASR copied to clipboard
SeacoParaformer的generate_hotwords_list函数有问题,导致hotword无法使用
以下代码中: ` elif not hotword_list_or_file.endswith(".txt"):
logging.info("Attempting to parse hotwords as str...")
hotword_list = []
hotword_str_list = []
for hw in hotword_list_or_file.strip().split():
hotword_str_list.append(hw)
hw_list = hw.strip().split()
if seg_dict is not None:
hw_list = seg_tokenize(hw_list, seg_dict)
hotword_list.append(tokenizer.tokens2ids(hw_list))
hotword_list.append([self.sos])
hotword_str_list.append("<s>")
logging.info("Hotword list: {}.".format(hotword_str_list))
`
hw_list = hw.strip().split()导致hw转为list后,tokens2ids只能获取错误的token,shape也成了(1,) 需要改为 hotword_list.append(tokenizer.tokens2ids(hw_list[0]))