I'm trying to code a script that detects speaker gender over time on a sound file.

I used ffmpeg to slice the file into few-seconds chunks, then I use this project to analyze each chunk.

The problem is that many of them doesn't have voice at all: it could be silences, ambiance music, various noises, etc. , on which the script still tries to guess the gender.

I tried to eliminate chunks where scores are lower than 90% but it produces many false positives (I guess it's because if the score given for one gender is bad but the score for the other one is a lot more bad, the algorithm could give a >90% certitude for the first one).

I there a way to get the accuracy of the result, or having scores for each gender independent to each other?

TypeError Traceback (most recent call last)
in
2 tensorboard = TensorBoard(log_dir="logs")
3 # define early stopping to stop training after 5 epochs of not improving
----> 4 early_stopping = EarlyStopping(mode="min", patience=5, restore_best_weights=True)
5
6 batch_size = 64

TypeError: init() got an unexpected keyword argument 'restore_best_weights'

load the dataset

X, y = load_data()

split the data into training, validation and testing sets

data = split_data(X, y, test_size=0.1, valid_size=0.1)

construct the model

model = create_model()

I dint get that. where to use the 12 GB dataset that I downloaded

Hello
I am looking for a tool that works direclty without me having to train any model, can this tool work if you provide me with the model direclty? is there a pre model provided?