python - 如何将微调模型的输出解码为文本？

Question

我已经对机器翻译模型进行了微调，并且正在尝试加载在训练期间保存的 pytorch_model.bin 模型检查点并预测单词的翻译。如何从transformers.modeling_outputs.Seq2SeqModelOutput 转换为普通文本？

model = AutoModel.from_pretrained('/content/drive/MyDrive/model', cache_dir=None)

 tokenizer = AutoTokenizer.from_pretrained('/content/drive/MyDrive/model', cache_dir=None)

model.eval()

inputs2 = tokenizer('word', return_tensors="pt")["input_ids"]

inputs2.data #results in =>
tensor([[ 1415,   259, 54622,     1]])

outputs = model(input_ids=inputs2, decoder_input_ids=inputs2)
type(outputs) #results in =>transformers.modeling_outputs.Seq2SeqModelOutput

**output_str = #translation of the input word**

标签： pythontorchhuggingface-transformersseq2seqhuggingface-tokenizers