【Hugging Face】Ep.2 初探新手村, 打造專屬的翻譯官

主題

本地端

version: "3.8"
services:
  jupyter:
    image: nvcr.io/nvidia/pytorch:22.12-py3
    tmpfs:
      - /tmp
    ports:
      - "8888:8888"
    volumes:
      - ./:/workspace
    runtime: nvidia
    command: jupyter notebook --ip=0.0.0.0 --port=8888 --allow-root --NotebookApp.token='test'

docker compose up -d

!pip install transformers

#  This tokenizer cannot be instantiated. Please make sure you have `sentencepiece` installed in order to use this tokenizer.
!pip install sentencepiece

!pip install sacremoses

from transformers import pipeline
translator = pipeline("translation", model='Helsinki-NLP/opus-mt-zh-en') #使用翻譯任務
translator('這是一個很困難的問題')

Google Colab

!pip install transformers

#  This tokenizer cannot be instantiated. Please make sure you have `sentencepiece` installed in order to use this tokenizer.
!pip install sentencepiece

!pip install sacremoses

from transformers import pipeline
translator = pipeline("translation", model='Helsinki-NLP/opus-mt-zh-en') #使用翻譯任務
translator('這是一個很困難的問題')

結語

更多關於【Hugging Face 系列】…

• 【Hugging Face】Ep.1 平凡人也能玩的起的AI平台
• 【Hugging Face】Ep.2 初探新手村, 打造專屬的翻譯官
• 【Hugging Face】Ep.3 前往Datasets掏金趣
• 【Hugging Face】Ep.4 文字與模型的轉換器Tokenizer
• 【Hugging Face】Ep.5 文字世界中的超能力語言英雄(Named Entity Recognition)
• 【Hugging Face】Ep.6 解決問題的專業級破關知識家(Question Answering)
• 【Hugging Face】Ep.7 以文生圖的魔幻製圖師(Text To Image)
• 【Hugging Face】Ep.8 專業的標準化推理家(Inference API)