Gender Cls Svm Ecapa Voxceleb

🚀 Gender Classification Model

This model combines the SpeechBrain ECAPA - TDNN speaker embedding model with an SVM classifier to predict speaker gender from audio input, trained and evaluated on multiple datasets.

🚀 Quick Start

This model combines the SpeechBrain ECAPA - TDNN speaker embedding model with an SVM classifier. It can predict speaker gender from audio input. The model has been trained and evaluated on the VoxCeleb2, Mozilla Common Voice v10.0, and TIMIT datasets.

✨ Features

• Accurate Prediction: Achieves high accuracy and F1 - score on multiple datasets like VoxCeleb2, Mozilla Common Voice v10.0, and TIMIT.
• Well - defined Input and Output: Accepts audio files as input and outputs gender predictions.
• Optimized Classifier: Uses a Support Vector Machine optimized through Optuna.

📦 Installation

You can install the package directly from GitHub:

pip install git+https://github.com/griko/voice-gender-classification.git

💻 Usage Examples

Basic Usage

from voice_gender_classification import GenderClassificationPipeline

# Load the pipeline
classifier = GenderClassificationPipeline.from_pretrained(
    "griko/gender_cls_svm_ecapa_voxceleb"
)

# Single file prediction
result = classifier("path/to/audio.wav")
print(result)  # ["female"] or ["male"]

# Batch prediction
results = classifier(["audio1.wav", "audio2.wav"])
print(results)  # ["female", "male", "female"]

📚 Documentation

Model Details

Training Data

The model was trained on the VoxCeleb2 dataset:

• Training set: 1,691 speakers (845 females, 846 males)
• Validation set: 785 speakers (396 females, 389 males)
• Test set: 1,647 speakers (828 females, 819 males)
• No speaker overlap between sets
• Audio preprocessing:
  • Converted to WAV format, single channel, 16kHz sampling rate, 256 kp/s bitrate
  • Applied SileroVAD for voice activity detection, taking the first voiced segment

Limitations

• The model was trained on celebrity voices from YouTube interviews.
• Performance may vary on different audio qualities or recording conditions.
• It is designed for binary gender classification only.

📄 License

This project is licensed under the Apache - 2.0 license.

📚 Citation

If you use this model in your research, please cite:

@misc{koushnir2025vanpyvoiceanalysisframework,
      title={VANPY: Voice Analysis Framework}, 
      author={Gregory Koushnir and Michael Fire and Galit Fuhrmann Alpert and Dima Kagan},
      year={2025},
      eprint={2502.17579},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2502.17579}, 
}