We may earn an affiliate commission when you visit our partners.
Course image
経知 神草

◇この講座でできるようになること

・(中級者向け)ZOOMやTeamsなどのオンライン会議レコーディングファイルもしくは音声ファイルからの

議事録自動作成(Colab)をPythonでモジュールとAPIの呼び出しのみ(非常に少ないコード)で行います。

・(中~上級者向け)Python Flaskを用いてローカル環境(インターネット接続なし)で動作する本格的な音声認識システムを

Read more

◇この講座でできるようになること

・(中級者向け)ZOOMやTeamsなどのオンライン会議レコーディングファイルもしくは音声ファイルからの

議事録自動作成(Colab)をPythonでモジュールとAPIの呼び出しのみ(非常に少ないコード)で行います。

・(中~上級者向け)Python Flaskを用いてローカル環境(インターネット接続なし)で動作する本格的な音声認識システムを

    構築できます。バックエンドはOpenAIのWhisperモデルなので、認識精度はかなり高いです。

◇この講座の構成

  1. 動画ファイル or 音声ファイルのアップロード

  2. 動画ファイルからの音声ファイル作成

  3. 音声ファイルからのテキスト抽出(音声認識)

  4. 音声認識テキストからの要点抽出(自動要約)←ChatGPT(gpt3.5/gpt4.0)にプロンプト生成してもらいました。

  5. 要点抽出結果のダウンロード

  6. Flask環境の構築

  7. ミニマムなFlaskアプリ

  8. Whisper_MIC

  9. Flask画面パーツ

  10. Stable Diffusionでfavicon

  11. Bootstrap

  12. Ajax

  13. デモ

  14. システム構成

  15. Whisper_MICとファイル連携

  16. 仕上げ

Enroll now

What's inside

Syllabus

Introduction
ffmpegをpythonから利用し、動画ファイルを音声ファイルに変換する方法
ZOOMでレコーディング
.mp4から.wav抽出
Read more
※補講 ZOOMで録画したMP4リソース (Gemini Proでスクリプトは生成)
音声ファイルからOpenAIのwhisperモジュールを利用して音声認識を行いテキストを生成する方法
PythonからWhisperを利用して音声認識を行う
ChatGPT API(gpt-3.5-turbo)を利用して、会議の要点を簡潔に出力させる方法を学ぶ
gpt-3.5-turboをpythonから呼び出し、会議の音声認識テキストから要点まとめを出力させる
ChatGPTに聞いてみた、議事録作成プロンプトの改善。
議事録ダウンロード
議事録を英語・中国語に翻訳
ローカルで音声認識を行うWebアプリの構築ができるようになることを目指します。
Flask環境の構築
ミニマムなFlaskアプリ

レクチャー11でgit cloneするWhisper_MICが講座収録時からソースの構造が大幅に改定されています。講座を進めるために過去のバージョン(2023/1/2のコミット)に戻す必要がありますので、こちらの補講では戻す方法をご説明いたします。


git cloneした後に以下コマンドを実行することで講座収録時のバージョンに戻せます。


git checkout 91afa6b0523e59e5d396dc69c86aa3a07ccf156e


レクチャー11: Whisper_MICの動画と合わせてこちらもご確認ください。


Whisper_MIC
12_Flask画面パーツ
Stable Diffusionでfavicon
Bootstrap/Set Interval/Style
Ajax request
最終的に作るもの
システム構成

仮想環境へ入るバッチの作成とシステム構成に従ったWebアプリのセットアップを行っていきます。

Whisperとファイル連携
仕上げ

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
Develops proficiency using Python and Flask, which are highly relevant for building speech-to-text applications
Teaches how to use OpenAI's Whisper model, which is recognized for its high accuracy in speech recognition
Builds skills in using ChatGPT, which is valuable for automating tasks and augmenting productivity
Emphasizes practical application through hands-on exercises and flask app development
Provides a strong foundation for learners interested in NLP and speech recognition
Requires prior experience in Python and basic understanding of NLP concepts

Save this course

Save ChatGPTとWhisperではじめるPythonローコード開発入門 to your list so you can find it easily later:
Save

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in ChatGPTとWhisperではじめるPythonローコード開発入門 with these activities:
**音声認識の基本を復習する:** 関連する用語と概念を復習する
この活動では、音声認識システムを理解するために必要な基礎知識を復習できます。
Show steps
  • オンラインリソースを読む
  • ビデオチュートリアルを視聴する
  • 関連用語のフラッシュカードを作成する
**教材のまとめ:** 講義動画、課題、リソースを整理する
この活動では、コース教材を整理し、後で簡単にアクセスできるようにします。
Show steps
  • 講義ファイルをダウンロードする
  • 課題をファイルに保存する
  • 関連リソースをブックマークする
**基礎の強化:** 音声認識APIを探索する
この練習では、OpenAIのWhisperなどの音声認識APIを操作し、それらの機能を理解できます。
Show steps
  • APIのドキュメントを読む
  • コードサンプルをテストする
  • 簡単なスクリプトを作成する
Five other activities
Expand to see all activities and additional details
Show all eight activities
**ツールの習得:** Whisprer MICの利用に関するチュートリアルを完了する
このチュートリアルでは、Whisper MICツールを使用して、ローカルトークを音声データに変換する方法を学びます。
Show steps
  • チュートリアル動画を視聴する
  • チュートリアルコードを実行する
  • Whisper MICの使い方を練習する
**ディスカッションに参加する:** クラスメートと概念や課題について議論する
この活動では、クラスメートと交流し、コースのトピックについて理解を深めることができます。
Show steps
  • ディスカッションフォーラムに参加する
  • 議論に参加する
  • 質問を投稿する
**コーディングスキルを磨く:** 音声認識機能付きWebアプリを構築する
このプロジェクトは、音声認識APIを使用してWebアプリを構築し、音声認識のスキルを向上させるのに役立ちます。
Show steps
  • プロジェクトのセットアップ
  • 音声認識機能の統合
  • ユーザーインターフェースの作成
  • アプリのデプロイ
**貢献する:** Whisper MICリポジトリにフィードバックを送信する
この活動では、Whisper MICプロジェクトに貢献し、開発プロセスの一部となることができます。
Show steps
  • バグや問題を特定する
  • 改善提案を作成する
  • フィードバックをリポジトリに送信する
**知識の共有:** 音声認識に関するブログ記事やチュートリアルを作成する
この活動では、コースのトピックをより深く理解し、他の人と知識を共有できます。
Show steps
  • トピックを選択する
  • リサーチを行う
  • コンテンツを作成する

Career center

Learners who complete ChatGPTとWhisperではじめるPythonローコード開発入門 will develop knowledge and skills that may be useful to these careers:
Natural Language Processing (NLP) Engineer
This course may be useful for your career as it will teach you about natural language processing and machine learning, providing you with the foundational knowledge needed to build and deploy NLP solutions. You will also gain experience using Python and Flask, which are popular tools in this field.
Speech Recognition Engineer
Speech Recognition Engineers design and develop systems that allow computers to recognize spoken language, similar to the kind of technology used in Siri or Alexa. This course may be of interest to you if you wish to pursue this career because it will teach you how to use OpenAI's Whisper model for speech recognition. You will also gain experience using Python, a common programming language in this field.
Software Developer
Software Developers design, develop, and maintain computer programs or applications using programming languages like Python, which is covered in this course. This is a very broad field with many different specializations, and this course may be helpful no matter which area you want to work in.
Software Engineer
Software Engineers apply engineering principles to the design, development, and maintenance of software systems, and they often use Python. This course may be helpful for your career because it will provide you with a solid foundation in Python and programming, which are essential skills for this role.
NLP Engineer
NLP Engineers build and maintain software that allows computers to understand and generate human language, and they use Python, the programming language covered in this course. For this profession, it is essential to have a solid understanding of natural language processing, machine learning, and deep learning, which is why taking this course may be beneficial.
Machine Learning Scientist
As a Machine Learning Scientist, you may be responsible for researching and developing new machine learning algorithms and models, which often involves using Python. This course will provide you with a solid foundation in Python, as well as experience using essential machine learning libraries such as scikit-learn. It may be helpful for your career as a Machine Learning Scientist.
Quantitative Analyst
Quantitative Analysts use mathematical and statistical modeling to assess the risk involved in financial investments, which requires strong programming skills. By taking this course, you will build a strong foundation in Python, which is a popular language for quantitative analysis. You will also gain experience using NumPy and Pandas for data analysis and manipulation, which may be useful for this role.
Data Scientist
Data Scientists use programming to analyze data and extract insights from it. This course may be helpful for your career as a Data Scientist because it will provide you with a solid foundation in Python, which is a common programming language used in this field.
Machine Learning Engineer
The field of Machine Learning Engineering is creating algorithms that can learn from data. To succeed in this role, you must have strong Python and programming skills, which is a focus of this course. Additionally, it will provide you with experience using OpenAI's Whisper model for speech recognition, which may be helpful for your career.
Product Manager
Product Managers are responsible for the success of a product throughout its lifecycle, which includes gathering requirements, designing the product, and overseeing its development. Taking this course may be helpful if you want to pursue this career because it will teach you Python, a common programming language used for product development. You will also gain experience building web applications using Flask, which may be useful for Product Managers.
Research Scientist
Research Scientists conduct scientific research in various fields, such as computer science and engineering. They often use Python for data analysis, modeling, and simulation. Taking this course may be helpful if you wish to pursue this career because it will provide you with experience using Python and other essential tools.
Operations Research Analyst
Operations Research Analysts use mathematical and analytical methods to solve complex problems in business and industry. For instance, they may use Python to create models that optimize supply chains or allocate resources. Taking this course can help you build a solid foundation in Python and programming, which are crucial skills for this field.
User Experience (UX) Designer
UX Designers create user-friendly and intuitive interfaces for websites and applications. Some UX Designers use Python to create prototypes or to automate tasks. By taking this course, you will build a strong foundation in Python, which may be useful for your career. You will also gain experience using Flask, a framework for building web applications, which may be helpful.
AI Engineer
Designing and developing software solutions for business problems is possible as an AI Engineer, a job that is rapidly expanding in fields like healthcare, finance, and transportation. This course may be of interest to you if you want to enter this field because it will provide you with foundational knowledge of NLP, a crucial element of AI. You will also learn Python, a key programming language for many AI tasks.
Data Analyst
Data Analysts use programming to clean, transform, manage, and visualize data. This role is responsible for translating raw data into insights. This program can teach you some programming essentials, as well as how to use Python to extract meaning from data, which could be useful for your career development.

Reading list

We've selected 13 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in ChatGPTとWhisperではじめるPythonローコード開発入門.
Provides a comprehensive introduction to Python programming, covering the basics of the language as well as more advanced topics such as object-oriented programming and data analysis. It valuable resource for beginners and experienced programmers alike.
Provides a comprehensive overview of natural language processing, covering topics such as tokenization, stemming, lemmatization, parsing, and machine translation. It valuable resource for anyone interested in learning more about NLP.
Provides a comprehensive overview of speech and language processing, covering topics such as phonetics, phonology, morphology, syntax, semantics, and pragmatics. It valuable resource for anyone interested in learning more about speech and language processing.
Provides a comprehensive overview of deep learning for natural language processing, covering topics such as word embeddings, recurrent neural networks, and transformers. It valuable resource for anyone interested in learning more about deep learning for NLP.
Provides a practical guide to natural language processing with TensorFlow. It covers topics such as text preprocessing, feature engineering, and model evaluation. It valuable resource for anyone interested in learning more about NLP in practice.
Provides a comprehensive overview of deep learning, including topics such as neural networks, convolutional neural networks, and recurrent neural networks. It valuable resource for anyone interested in the latest advances in deep learning.
Provides a comprehensive introduction to data analysis using Python, covering topics such as data cleaning, data manipulation, and data visualization. It valuable resource for anyone interested in using Python for data analysis.
Provides a practical introduction to deep learning for coders, using the fastai and PyTorch libraries. It valuable resource for anyone interested in using deep learning to solve real-world problems.
Provides a collection of recipes for solving machine learning problems using Python. It valuable resource for anyone interested in using Python for machine learning.
Provides a comprehensive introduction to web development using Flask, a popular Python web framework. It valuable resource for anyone interested in building web applications with Python.
Provides a practical introduction to deep learning using Python and the Keras library. It valuable resource for anyone interested in using deep learning to solve real-world problems.
Provides a comprehensive overview of the Natural Language Toolkit (NLTK), a popular Python library for natural language processing. It valuable resource for anyone interested in using NLTK to solve real-world problems.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Here are nine courses similar to ChatGPTとWhisperではじめるPythonローコード開発入門.
アウトプットで確実に身につける薬局英会話講座!調剤の現場ですぐに使える英語をマスターする特訓コース(ネイティブ音声付...
Most relevant
OpenAI API 完全マスターガイド: ChatGPTによるチャットボット開発や画像生成、音声認識を基礎から学ぶ
Most relevant
実例でわかる JavaScript 初心者講座
Most relevant
世界を変えるボンバスティックなPhotoshop講座
Most relevant
Google Drive 日本語版
Most relevant
7. Python を使ったサイバーセキュリティ タスクの自動化
Most relevant
自然言語処理とチャットボット: AIによる文章生成と会話エンジン開発
Most relevant
【英文法で学ぶ】句節英会話 -文型の知識を土台に英会話/英作文力を磨く
Most relevant
【グローバル人材の英会話】外資系1年目のビジネス英語 マスターコース
Most relevant
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2024 OpenCourser