test

语帆

2024-02-21 a0ffe57b05679d91e56227ce1109a5d725d93192

 funasr/auto/auto_model.py

@@ -20,8 +20,11 @@
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`")
import pdb

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
@@ -206,13 +209,16 @@
        kwargs = self.kwargs if kwargs is None else kwargs
        kwargs.update(cfg)
        model = self.model if model is None else model
        model.eval()
        pdb.set_trace()

        batch_size = kwargs.get("batch_size", 1)
        # if kwargs.get("device", "cpu") == "cpu":
        #     batch_size = 1
        
        key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=kwargs.get("data_type", None), key=key)
        
        pdb.set_trace()

        speed_stats = {}
        asr_result_list = []
        num_samples = len(data_list)
@@ -220,20 +226,25 @@
        pbar = tqdm(colour="blue", total=num_samples, dynamic_ncols=True) if not disable_pbar else None
        time_speech_total = 0.0
        time_escape_total = 0.0
        pdb.set_trace()
        for beg_idx in range(0, num_samples, batch_size):
            pdb.set_trace()
            end_idx = min(num_samples, beg_idx + batch_size)
            data_batch = data_list[beg_idx:end_idx]
            key_batch = key_list[beg_idx:end_idx]
            batch = {"data_in": data_batch, "key": key_batch}
            pdb.set_trace()
            if (end_idx - beg_idx) == 1 and kwargs.get("data_type", None) == "fbank": # fbank
                batch["data_in"] = data_batch[0]
                batch["data_lengths"] = input_len
        
            time1 = time.perf_counter()
            with torch.no_grad():
                pdb.set_trace()
                results, meta_data = model.inference(**batch, **kwargs)
            time2 = time.perf_counter()
            
            pdb.set_trace()
            asr_result_list.extend(results)

            # batch_data_time = time_per_frame_s * data_batch_i["speech_lengths"].sum().item()
@@ -385,11 +396,11 @@
                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 +420,7 @@
                                                        result['timestamp'], \
                                                        result['raw_text'])
                result['sentence_info'] = sentence_list
            del result['spk_embedding']
                    
            result["key"] = key
            results_ret_list.append(result)