Create initial project structure with README.md, requirements.txt and .gitignore#3
Merged
alexcerezo merged 1 commit intomainfrom Jul 20, 2025
Conversation
Copilot
AI
changed the title
[WIP] Crear README.md completo desde cero
Create initial project structure with README.md, requirements.txt and .gitignore
Jul 20, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR creates the foundational structure for the Fine-Tuning Sign Language project by adding three essential files from scratch due to a conflict in the previous Pull Request.
Files Added
📖 README.md
Complete project documentation including:
📦 requirements.txt
Essential dependencies for the project:
google-generativeai>=0.3.0- Google Gemini API clientpython-dotenv>=1.0.0- Environment variable management🔒 .gitignore
Comprehensive Python project gitignore including:
.envfiles)Problem Context
The sign language recognition device works correctly but generates text with excessive repeated characters. Some words can be ambiguous based on context:
This project will use Google Gemini's fine-tuning capabilities to solve this text correction problem through a structured 4-phase approach.
Next Steps
Phase 1 is now complete with the basic project structure. The next phase will involve:
data_generator.pyfor creating training datasetsFixes the repository structure needed to continue development following the established roadmap.
This pull request was created as a result of the following prompt from Copilot chat.
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.