QQQ
3Q!
📚 【翻訳モデル】200の言語を翻訳できるNLLBモデル体験 LM2_1
PDF ファイル処理(pdfplumber)
Word ファイル処理(python-docx)
Excel ファイル処理(openpyxl + pandas)
Python 3.10.0
user ~
? python --version
Python 3.10.0
conda
? conda info --env
# conda environments:
#
base F:\Users\user\anaconda3
tts F:\Users\user\anaconda3\envs\tts
CUDA環境の準備
? nvidia-smi
Thu Jun 26 23:48:51 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 573.23 Driver Version: 573.23 CUDA Version: 12.8 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Driver-Model | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 Quadro P4000 WDDM | 00000000:9E:00.0 On | N/A |
| 52% 55C P0 28W / 105W | 1889MiB / 8192MiB | 4% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 13156 C+G ...Chrome\Application\chrome.exe N/A |
| 0 N/A N/A 15672 C+G C:\Windows\explorer.exe N/A |
| 0 N/A N/A 19416 C+G ...Chrome\Application\chrome.exe N/A |
| 0 N/A N/A 19984 C+G ...ice\root\Office16\WINWORD.EXE N/A |
| 0 N/A N/A 20280 C+G ...indows\System32\ShellHost.exe N/A |
| 0 N/A N/A 22624 C+G ...yb3d8bbwe\WindowsTerminal.exe N/A |
| 0 N/A N/A 24804 C+G ...App_cw5n1h2txyewy\LockApp.exe N/A |
| 0 N/A N/A 30924 C+G ....0.3179.73\msedgewebview2.exe N/A |
| 0 N/A N/A 31284 C+G ...les\Tencent\Weixin\Weixin.exe N/A |
| 0 N/A N/A 34656 C+G ...y\StartMenuExperienceHost.exe N/A |
| 0 N/A N/A 34848 C+G ...5n1h2txyewy\TextInputHost.exe N/A |
| 0 N/A N/A 36656 C+G ...acted\runtime\WeChatAppEx.exe N/A |
| 0 N/A N/A 37184 C+G ...xyewy\ShellExperienceHost.exe N/A |
| 0 N/A N/A 37272 C+G ..._cw5n1h2txyewy\SearchHost.exe N/A |
| 0 N/A N/A 37436 C+G C:\Windows\explorer.exe N/A |
| 0 N/A N/A 38356 C+G C:\Windows\explorer.exe N/A |
| 0 N/A N/A 38864 C+G ...m Files\RustDesk\RustDesk.exe N/A |
| 0 N/A N/A 41132 C+G C:\Windows\explorer.exe N/A |
| 0 N/A N/A 42296 C+G ...t\Edge\Application\msedge.exe N/A |
| 0 N/A N/A 47356 C+G ...al\Programs\cursor\Cursor.exe N/A |
+-----------------------------------------------------------------------------------------+
GPU:Quadro P4000,8GB RAM,ドライバーバージョンとCUDAは正常らしい(Driver 573.23,CUDA 12.8)
? pip show ctranslate2
Name: ctranslate2
Version: 4.6.0
Summary: Fast inference engine for Transformer models
Home-page: https://opennmt.net
Author: OpenNMT
Author-email:
License: MIT
Location: c:\users\user\appdata\roaming\python\python310\site-packages
Requires: numpy, pyyaml, setuptools
Required-by:
CUDAをリセットアップする。
user I:\DocTranslate\scripts via 🐍 v3.10.0
? pip uninstall ctranslate2
Found existing installation: ctranslate2 4.6.0
Uninstalling ctranslate2-4.6.0:
Would remove:
c:\users\user\appdata\roaming\python\python310\scripts\ct2-fairseq-converter.exe
c:\users\user\appdata\roaming\python\python310\scripts\ct2-marian-converter.exe
c:\users\user\appdata\roaming\python\python310\scripts\ct2-openai-gpt2-converter.exe
c:\users\user\appdata\roaming\python\python310\scripts\ct2-opennmt-py-converter.exe
c:\users\user\appdata\roaming\python\python310\scripts\ct2-opennmt-tf-converter.exe
c:\users\user\appdata\roaming\python\python310\scripts\ct2-opus-mt-converter.exe
c:\users\user\appdata\roaming\python\python310\scripts\ct2-transformers-converter.exe
c:\users\user\appdata\roaming\python\python310\site-packages\ctranslate2-4.6.0.dist-info\*
c:\users\user\appdata\roaming\python\python310\site-packages\ctranslate2\*
Proceed (Y/n)? y
Successfully uninstalled ctranslate2-4.6.0
user I:\DocTranslate\scripts via 🐍 v3.10.0 took 16s
? pip install ctranslate2[cuda]
Defaulting to user installation because normal site-packages is not writeable
Collecting ctranslate2[cuda]
Downloading ctranslate2-4.6.0-cp310-cp310-win_amd64.whl.metadata (10 kB)
WARNING: ctranslate2 4.6.0 does not provide the extra 'cuda'
Requirement already satisfied: setuptools in c:\program files\python310\lib\site-packages (from ctranslate2[cuda]) (57.4.0)
Requirement already satisfied: numpy in c:\program files\python310\lib\site-packages (from ctranslate2[cuda]) (1.22.0)
Requirement already satisfied: pyyaml<7,>=5.3 in c:\program files\python310\lib\site-packages (from ctranslate2[cuda]) (6.0.2)
Downloading ctranslate2-4.6.0-cp310-cp310-win_amd64.whl (19.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 19.5/19.5 MB 11.3 MB/s eta 0:00:00
Installing collected packages: ctranslate2
Successfully installed ctranslate2-4.6.0
環境確認
user I:\DocTranslate\scripts via 🐍 v3.10.0
? python .\test.py
CTranslate2 CUDA 初期化成功!
? conda create -n doctrans python=3.10
Retrieving notices: done
Channels:
- defaults
Platform: win-64
Collecting package metadata (repodata.json): done
Solving environment: done
## Package Plan ##
environment location: C:\Users\user\.conda\envs\doctrans
added / updated specs:
- python=3.10
The following packages will be downloaded:
package | build
---------------------------|-----------------
expat-2.7.1 | h8ddb27b_0 259 KB
python-3.10.18 | h981015d_0 16.2 MB
tk-8.6.14 | h5e9d12e_1 3.5 MB
------------------------------------------------------------
Total: 20.0 MB
done
#
# To activate this environment, use
#
# $ conda activate doctrans
#
# To deactivate an active environment, use
#
# $ conda deactivate
# Python環境をアクティブする。
user ~ took 58s
? conda activate doctrans
user ~ took 6s
? conda install openpyxl pandas -y
Channels:
- defaults
Platform: win-64
Collecting package metadata (repodata.json): done
# Condaがpdfplumber,python-docx 二つライブラリを見つかりませんでした。だから、pipで手動的にセットアップすること。
user ~ took 6s
? pip install pdfplumber python-docx
Defaulting to user installation because normal site-packages is not writeable
Collecting pdfplumber
Downloading pdfplumber-0.11.7-py3-none-any.whl.metadata (42 kB)
Collecting python-docx
Downloading python_docx-1.2.0-py3-none-any.whl.metadata (2.0 kB)
Collecting pdfminer.six==20250506 (from pdfplumber)
Downloading pdfminer_six-20250506-py3-none-any.whl.metadata (4.2 kB)
Requirement already satisfied: Pillow>=9.1 in c:\program files\python310\lib\site-packages (from pdfplumber) (11.0.0)
Collecting pypdfium2>=4.18.0 (from pdfplumber)
Downloading pypdfium2-4.30.1-py3-none-win_amd64.whl.metadata (48 kB)
Requirement already satisfied: charset-normalizer>=2.0.0 in c:\program files\python310\lib\site-packages (from pdfminer.six==20250506->pdfplumber) (3.4.2)
Collecting cryptography>=36.0.0 (from pdfminer.six==20250506->pdfplumber)
Downloading cryptography-45.0.4-cp37-abi3-win_amd64.whl.metadata (5.7 kB)
Requirement already satisfied: lxml>=3.1.0 in c:\program files\python310\lib\site-packages (from python-docx) (5.3.2)
Requirement already satisfied: typing_extensions>=4.9.0 in c:\program files\python310\lib\site-packages (from python-docx) (4.13.2)
Requirement already satisfied: cffi>=1.14 in c:\program files\python310\lib\site-packages (from cryptography>=36.0.0->pdfminer.six==20250506->pdfplumber) (1.17.1)
Requirement already satisfied: pycparser in c:\program files\python310\lib\site-packages (from cffi>=1.14->cryptography>=36.0.0->pdfminer.six==20250506->pdfplumber) (2.22)
Downloading pdfplumber-0.11.7-py3-none-any.whl (60 kB)
Downloading pdfminer_six-20250506-py3-none-any.whl (5.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.6/5.6 MB 11.4 MB/s eta 0:00:00
Downloading python_docx-1.2.0-py3-none-any.whl (252 kB)
Downloading cryptography-45.0.4-cp37-abi3-win_amd64.whl (3.4 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.4/3.4 MB 11.2 MB/s eta 0:00:00
Downloading pypdfium2-4.30.1-py3-none-win_amd64.whl (3.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.0/3.0 MB 10.8 MB/s eta 0:00:00
Installing collected packages: python-docx, pypdfium2, cryptography, pdfminer.six, pdfplumber
━━━━━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/5 [pypdfium2] WARNING: The script pypdfium2.exe is installed in 'C:\Users\user\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━ 4/5 [pdfplumber] WARNING: The script pdfplumber.exe is installed in 'C:\Users\user\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
Successfully installed cryptography-45.0.4 pdfminer.six-20250506 pdfplumber-0.11.7 pypdfium2-4.30.1 python-docx-1.2.0
🔍 セットアップ説明:
ライブラリ名 説明
pdfplumber PDFファイル内容取得(pdfminer.sixにより)
python-docx .docx Wordファイルの読み取り、書込み
openpyxl .xlsx Excelファイルの読み取り、書込み
pandas データ処理、Excel内容を補助する。
最後チェック!
**user ~
? python -c "import pdfplumber; import docx; print('OK')"
OK
user ~ took 6s
? conda list | findstr openpyxl
openpyxl 3.1.5 py312h827c3e9_0
user ~ took 6s
? conda list | findstr pandas
pandas 2.2.2 py312h0158946_0**
次は、翻訳をしよう!