IELTS Speech Analyzer is a web application that helps users improve their IELTS speaking skills by analyzing audio recordings and providing detailed feedback.
- Upload MP4 video files for analysis
- Convert video to audio for processing
- Transcribe speech using Whisper AI model
- Analyze speech based on IELTS Speaking Band Descriptors
- Provide detailed feedback on Fluency and Coherence, Lexical Resource, and Grammatical Range and Accuracy
- Generate an estimated IELTS band score
- Offer specific suggestions for improvement
- Store and manage recent analyses
- Python 3.7+
- Flask
- MoviePy
- Groq API access
- Whisper AI model
-
Clone the repository:
git clone https://github.com/Yc3t/IELTS-speech-analyzer cd ielts-speech-analyzer
-
Create a virtual environment and activate it:
python -m venv venv source venv/bin/activate # On Windows, use `venv\Scripts\activate`
-
Install the required packages:
pip install -r requirements.txt
-
Create a
.env
file in the project root and add your Groq API key:GROQ_API_KEY=your_groq_api_key_here
-
create a
data
folder in the directory
-
Start the Flask server:
python app.py
-
Open a web browser and navigate to
http://localhost:5000
-
Use the interface to upload an MP4 file of your IELTS speaking practice
-
Wait for the analysis to complete
-
Review the detailed feedback and suggestions for improvement
app.py
: Main Flask applicationstatic/
: Contains CSS, JavaScript, and image filestemplates/
: Contains HTML templatesdata/
: Stores uploaded audio files and analysis resultsrequirements.txt
: List of Python dependencies
S2T.py
: aislated speech to text functionality