OoKyleoO

Request for checkpoints of feature extractor in MutimodalVideoTag

2

Hi! Is there any chance to provide the checkpoints of feature extractor in MutimodalVideoTag plz~

[BUG] KeyError: 'total'，找到错误来源

1

一个可能的错误是，当搜索某些字段的时候， 搜索出来的字段没有“约”字：找到相关图片190张 而parser的init文件里面parse_pic方法： total = int( soup.find("div", id="resultInfo") .text.split("约")[-1] .split("张")[0] .replace(",", "") ) 会导致无法转int 应该改为 total = int(''.join(re.findall(r'\d+', soup.find("div", id="resultInfo").text)))

给任意无人声音频 `audio_model = AutoModel( model="paraformer-zh", model_revision="v2.0.4", vad_model="fsmn-vad", vad_model_revision="v2.0.4", punc_model="ct-punc-c", punc_model_revision="v2.0.4" ) audio_model.generate(input=[audio], batch_size_s=200, is_final=True, sentence_timestamp=True)` 报错： RuntimeError: Expected tensor for argument #1 'indices' to have one of the following scalar...

ERROR: The request could not be satisfied 400 ERROR The request could not be satisfied. Bad request. We can't connect to the server for this app or website at this...