bugfix

游雁

2024-02-21 4cf44a89f808411a0616c8ed92c3afae3d3e371a

 funasr/auto/auto_model.py

@@ -20,7 +20,10 @@
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.utils.timestamp_tools import timestamp_sentence
from funasr.models.campplus.utils import sv_chunk, postprocess, distribute_spk
from funasr.models.campplus.cluster_backend import ClusterBackend
try:
    from funasr.models.campplus.cluster_backend import ClusterBackend
except:
    print("If you want to use the speaker diarization, please `pip install hdbscan`")


def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):
@@ -171,7 +174,7 @@
        # build model
        model_class = tables.model_classes.get(kwargs["model"])
        model = model_class(**kwargs, **kwargs["model_conf"], vocab_size=vocab_size)
        model.eval()
        
        model.to(device)
        
        # init_param
@@ -206,6 +209,7 @@
        kwargs = self.kwargs if kwargs is None else kwargs
        kwargs.update(cfg)
        model = self.model if model is None else model
        model.eval()

        batch_size = kwargs.get("batch_size", 1)
        # if kwargs.get("device", "cpu") == "cpu":
@@ -396,20 +400,20 @@
                    for res, vadsegment in zip(restored_data, vadsegments):
                        sentence_list.append({"start": vadsegment[0],\
                                                "end": vadsegment[1],
                                                "sentence": res['raw_text'],
                                                "sentence": res['text'],
                                                "timestamp": res['timestamp']})
                elif self.spk_mode == 'punc_segment':
                    sentence_list = timestamp_sentence(punc_res[0]['punc_array'], \
                                                        result['timestamp'], \
                                                        result['raw_text'])
                                                        result['text'])
                distribute_spk(sentence_list, sv_output)
                result['sentence_info'] = sentence_list
            elif kwargs.get("sentence_timestamp", False):
                sentence_list = timestamp_sentence(punc_res[0]['punc_array'], \
                                                        result['timestamp'], \
                                                        result['raw_text'])
                                                        result['text'])
                result['sentence_info'] = sentence_list
            del result['spk_embedding']
            if "spk_embedding" in result: del result['spk_embedding']
                    
            result["key"] = key
            results_ret_list.append(result)