数据集:

3Aaishell 3Aamazon_reviews_multi 3Aami 3Abanking77 3Ac4 3Acnn_dailymail 3Aconll2003 3Adihard 3Aemotion 3Afunsd 3Afunsd-layoutlmv3 3Aglue 3Aimagefolder 3Arepere 3Asamsum 3Asquad 3Atiiuae/falcon-refinedweb 3Avoxceleb 3Avoxconverse 3Awikiann 3Awikiann-conll2003 3Axsum aishell amazon_reviews_multi ami banking77 c4 cnn_dailymail conll2003 dihard emotion funsd funsd-layoutlmv3 glue imagefolder repere samsum squad tiiuae/falcon-refinedweb voxceleb voxconverse wikiann wikiann-conll2003 xsum

预印本库:

arxiv:1911.02150 arxiv:2005.14165 arxiv:2012.01477 arxiv:2104.04045 arxiv:2104.09864 arxiv:2205.05131 arxiv:2205.14135 arxiv:2210.11416

其他:

audio Trained with AutoTrain AutoTrain Compatible bart bert bloom clip Carbon Emissions custom_code deberta-v2 distilbert endpoints-template generated_from_trainer generic gptj layoutlm lilt LLM Eval Results optimum overlapped-speech-detection pyannote pyannote-audio-model pyannote-audio-pipeline RefinedWeb resegmentation roberta sagemaker speaker speaker-change-detection speaker-diarization speaker-segmentation speech t5 text-generation-inference 文生文 vision vision-encoder-decoder voice

语言:

de en

许可:

apache-2.0 mit

类库:

ONNX pyannote.audio PyTorch TensorBoard TensorFlow Transformers

任务:

other 问答 摘要生成 文本分类 文本生成 标记分类 语音活动检测 零样本图像分类