Skip to content

PyTorch-based RNN with an attention mechanism for estimating syllable counts in audio samples

Notifications You must be signed in to change notification settings

v-perfilev/syllable_counter

Repository files navigation

Syllable Counter

This project develops a deep learning model designed to accurately count syllables in audio recordings of varying lengths. Utilizing a recurrent neural network architecture enhanced with an attention mechanism, the model processes spectrogram tensors to predict the syllable count. The model is built with PyTorch.

Requirements

  • ffmpeg (!!!)
  • PyTorch
  • PyAudio
  • Matplotlib

About

PyTorch-based RNN with an attention mechanism for estimating syllable counts in audio samples

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published