update

shixian.shi

2023-06-27 b0f4910de6dc91c13828026fb5bdd4f15d8636f3

 funasr/bin/asr_infer.py

@@ -285,6 +285,7 @@
            nbest: int = 1,
            frontend_conf: dict = None,
            hotword_list_or_file: str = None,
            clas_scale: float = 1.0,
            decoding_ind: int = 0,
            **kwargs,
    ):
@@ -377,10 +378,12 @@
        self.asr_train_args = asr_train_args
        self.converter = converter
        self.tokenizer = tokenizer
        self.cmvn_file = cmvn_file

        # 6. [Optional] Build hotword list from str, local file or url
        self.hotword_list = None
        self.hotword_list = self.generate_hotwords_list(hotword_list_or_file)
        self.clas_scale = clas_scale

        is_use_lm = lm_weight != 0.0 and lm_file is not None
        if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
@@ -445,16 +448,20 @@
        pre_token_length = pre_token_length.round().long()
        if torch.max(pre_token_length) < 1:
            return []
        if not isinstance(self.asr_model, ContextualParaformer) and not isinstance(self.asr_model,
                                                                                   NeatContextualParaformer):
        if not isinstance(self.asr_model, ContextualParaformer) and \
            not isinstance(self.asr_model, NeatContextualParaformer):
            if self.hotword_list:
                logging.warning("Hotword is given but asr model is not a ContextualParaformer.")
            decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds,
                                                                     pre_token_length)
            decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
        else:
            decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds,
                                                                     pre_token_length, hw_list=self.hotword_list)
            decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, 
                                                                     enc_len, 
                                                                     pre_acoustic_embeds,
                                                                     pre_token_length, 
                                                                     hw_list=self.hotword_list,
                                                                     clas_scale=self.clas_scale)
            decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]

        if isinstance(self.asr_model, BiCifParaformer):
@@ -519,6 +526,44 @@
        return results

    def generate_hotwords_list(self, hotword_list_or_file):
        def load_seg_dict(seg_dict_file):
            seg_dict = {}
            assert isinstance(seg_dict_file, str)
            with open(seg_dict_file, "r", encoding="utf8") as f:
                lines = f.readlines()
                for line in lines:
                    s = line.strip().split()
                    key = s[0]
                    value = s[1:]
                    seg_dict[key] = " ".join(value)
            return seg_dict

        def seg_tokenize(txt, seg_dict):
            pattern = re.compile(r'^[\u4E00-\u9FA50-9]+$')
            out_txt = ""
            for word in txt:
                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>" + " "
            return out_txt.strip().split()

        seg_dict = None
        if self.cmvn_file is not None:
            model_dir = os.path.dirname(self.cmvn_file)
            seg_dict_file = os.path.join(model_dir, 'seg_dict')
            if os.path.exists(seg_dict_file):
                seg_dict = load_seg_dict(seg_dict_file)
            else:
                seg_dict = None
        # for None
        if hotword_list_or_file is None:
            hotword_list = None
@@ -530,8 +575,11 @@
            with codecs.open(hotword_list_or_file, 'r') as fin:
                for line in fin.readlines():
                    hw = line.strip()
                    hw_list = hw.split()
                    if seg_dict is not None:
                        hw_list = seg_tokenize(hw_list, seg_dict)
                    hotword_str_list.append(hw)
                    hotword_list.append(self.converter.tokens2ids([i for i in hw]))
                    hotword_list.append(self.converter.tokens2ids(hw_list))
                hotword_list.append([self.asr_model.sos])
                hotword_str_list.append('<s>')
            logging.info("Initialized hotword list from file: {}, hotword list: {}."
@@ -551,8 +599,11 @@
            with codecs.open(hotword_list_or_file, 'r') as fin:
                for line in fin.readlines():
                    hw = line.strip()
                    hw_list = hw.split()
                    if seg_dict is not None:
                        hw_list = seg_tokenize(hw_list, seg_dict)
                    hotword_str_list.append(hw)
                    hotword_list.append(self.converter.tokens2ids([i for i in hw]))
                    hotword_list.append(self.converter.tokens2ids(hw_list))
                hotword_list.append([self.asr_model.sos])
                hotword_str_list.append('<s>')
            logging.info("Initialized hotword list from file: {}, hotword list: {}."
@@ -564,7 +615,10 @@
            hotword_str_list = []
            for hw in hotword_list_or_file.strip().split():
                hotword_str_list.append(hw)
                hotword_list.append(self.converter.tokens2ids([i for i in hw]))
                hw_list = hw.strip().split()
                if seg_dict is not None:
                    hw_list = seg_tokenize(hw_list, seg_dict)
                hotword_list.append(self.converter.tokens2ids(hw_list))
            hotword_list.append([self.asr_model.sos])
            hotword_str_list.append('<s>')
            logging.info("Hotword list: {}.".format(hotword_str_list))
@@ -1636,8 +1690,10 @@
        )
        frontend = None
        if asr_train_args.frontend is not None and asr_train_args.frontend_conf is not None:
            if asr_train_args.frontend == 'wav_frontend':
                frontend = WavFrontend(cmvn_file=cmvn_file, **asr_train_args.frontend_conf)
            from funasr.tasks.sa_asr import frontend_choices
            if asr_train_args.frontend == 'wav_frontend' or asr_train_args.frontend == "multichannelfrontend":
                frontend_class = frontend_choices.get_class(asr_train_args.frontend)
                frontend = frontend_class(cmvn_file=cmvn_file, **asr_train_args.frontend_conf).eval()
            else:
                frontend_class = frontend_choices.get_class(asr_train_args.frontend)
                frontend = frontend_class(**asr_train_args.frontend_conf).eval()