takikhasan / english-accent-detection

A CNN model that uses MFCCs from the wav files to train, test & predict the native language of the speaker.

English Accent Detection

A CNN model that uses MFCCs from the wav files to train, test & predict the native language of the speaker.

Setup & Requirements • Folder Structure & Code • Running The Project

💣 Setup & Requirements

👾 Editor & Environment Setup

• Install Miniconda or Anaconda
• Install PyCharm
• Open PyCharm and hit New Project
• In the Create Project window, select New environment using Conda and Python version: 3.8
• Hit Create

🎓 Requirements

After creating, the project will open. From the bottom, click on Terminal. Then:

• conda install numba
• pip install librosa
• pip install matplotlib
• pip install --upgrade pip
• pip install tensorflow
• pip install easygui

📜 Folder Structure & Code

• Copy and paste all three Python scripts from this repository to the PyCharm project folder you just created
• Copy and paste the folder Full Dataset wav from this link to the same PyCharm project folder

🌟 Running The Project

• Use Alt+Shift+F10 from inside PyCharm to run each file in the following order
• Run prepare_dataset.py to preprocess the dataset and create a json file with all processed data
• Run cnn_train_test.py to train the CNN model and save it
• Run predict.py to load the saved CNN model and use it to classify any wav file selected using the file explorer

english-accent-detection's Issues

Issue with prepare_dataset.py running

In the first step of running the prepare_dataset.py file I am getting the following issue:
Processing: Arabic
Traceback (most recent call last):
File "C:\Users\yaswa\PycharmProjects\pythonProject1\prepare_dataset.py", line 79, in
save_mfcc(DATASET_PATH, JSON_PATH, segment_duration=3) # segment_duration in seconds
File "C:\Users\yaswa\PycharmProjects\pythonProject1\prepare_dataset.py", line 63, in save_mfcc
mfcc = librosa.feature.mfcc(signal[start:finish], sample_rate, n_mfcc=num_mfcc, n_fft=n_fft,
TypeError: mfcc() takes 0 positional arguments but 2 positional arguments (and 1 keyword-only argument) were given

Can you please resolve the above issue.