From b0f4910de6dc91c13828026fb5bdd4f15d8636f3 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 27 六月 2023 20:11:30 +0800
Subject: [PATCH] update

---
 funasr/bin/asr_infer.py |   84 +++++++++++++++++++++++++++++++++++-------
 1 files changed, 70 insertions(+), 14 deletions(-)

diff --git a/funasr/bin/asr_infer.py b/funasr/bin/asr_infer.py
index e0e2c09..0ce8dd8 100644
--- a/funasr/bin/asr_infer.py
+++ b/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,
     ):
@@ -316,7 +317,7 @@
         # 2. Build Language model
         if lm_train_config is not None:
             lm, lm_train_args = build_model_from_file(
-                lm_train_config, lm_file, device
+                lm_train_config, lm_file, None, device, task_name="lm"
             )
             scorers["lm"] = lm.lm
 
@@ -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))
@@ -636,7 +690,7 @@
         # 2. Build Language model
         if lm_train_config is not None:
             lm, lm_train_args = build_model_from_file(
-                lm_train_config, lm_file, device
+                lm_train_config, lm_file, None, device, task_name="lm"
             )
             scorers["lm"] = lm.lm
 
@@ -1120,7 +1174,7 @@
         # 2. Build Language model
         if lm_train_config is not None:
             lm, lm_train_args = build_model_from_file(
-                lm_train_config, lm_file, device
+                lm_train_config, lm_file, None, device, task_name="lm"
             )
             lm.to(device)
             scorers["lm"] = lm.lm
@@ -1343,7 +1397,7 @@
 
         if lm_train_config is not None:
             lm, lm_train_args = build_model_from_file(
-                lm_train_config, lm_file, device
+                lm_train_config, lm_file, None, device, task_name="lm"
             )
             lm_scorer = lm.lm
         else:
@@ -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()
@@ -1659,7 +1715,7 @@
         # 2. Build Language model
         if lm_train_config is not None:
             lm, lm_train_args = build_model_from_file(
-                lm_train_config, lm_file, None, device
+                lm_train_config, lm_file, None, device, task_name="lm"
             )
             scorers["lm"] = lm.lm
 

--
Gitblit v1.9.1