aishell example

游雁

2024-02-19 94de39dde2e616a01683c518023d0fab72b4e103

 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):
@@ -88,7 +91,7 @@
class AutoModel:
    
    def __init__(self, **kwargs):
        if kwargs.get("disable_log", False):
        if not kwargs.get("disable_log", False):
            tables.print()
        
        model, kwargs = self.build_model(**kwargs)
@@ -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":
@@ -385,11 +389,11 @@
                result["text"] = punc_res[0]["text"]
                
            # speaker embedding cluster after resorted
            if self.spk_model is not None:
            if self.spk_model is not None and kwargs.get('return_spk_res', True):
                all_segments = sorted(all_segments, key=lambda x: x[0])
                spk_embedding = result['spk_embedding']
                labels = self.cb_model(spk_embedding.cpu(), oracle_num=kwargs['preset_spk_num'])
                del result['spk_embedding']
                labels = self.cb_model(spk_embedding.cpu(), oracle_num=kwargs.get('preset_spk_num', None))
                # del result['spk_embedding']
                sv_output = postprocess(all_segments, None, labels, spk_embedding.cpu())
                if self.spk_mode == 'vad_segment':  # recover sentence_list
                    sentence_list = []
@@ -409,6 +413,7 @@
                                                        result['timestamp'], \
                                                        result['raw_text'])
                result['sentence_info'] = sentence_list
            del result['spk_embedding']
                    
            result["key"] = key
            results_ret_list.append(result)