Wav2vec2 Xlsr English Speech Emotion Recognition

🚀 Emotion Recognition in English Using RAVDESS and Wav2Vec 2.0

This model is designed to extract emotions from audio recordings. It leverages the RAVDESS dataset with English audio and can recognize six emotions: anger, disgust, fear, happiness, sadness, and surprise.

🚀 Quick Start

Use the code below to get started with the model. [More Information Needed]

✨ Features

• Extract emotions from English audio recordings.
• Recognize six different emotions: anger, disgust, fear, happiness, sadness, and surprise.
• Recreate the work of a Greek emotion extractor using a pre - trained Wav2Vec2 model.

📚 Documentation

Model Details

Model Description

• Adapted from: Emotion Recognition in Greek
• Model type: NN with CTC
• Language(s) (NLP): English
• Finetuned from model: wav2vec2

Training Details

Training Data

The RAVDESS dataset was split into training, validation and test sets with 60, 20 and 20 splits, respectively.

Training Procedure

The fine - tuning process was centred on four hyper - parameters:

• the number of batches (4, 8),
• gradient accumulation steps (GAS) (2, 4, 6, 8),
• number of epochs (10, 20) and
• the learning rate (1e - 3, 1e - 4, 1e - 5).

Each experiment was repeated 10 times.

Evaluation

The set of hyper - parameters resulting in the best performance is: 4 batches, 4 GAS, 10 epochs and 1e - 4 learning rate

Testing

The model was retrained on the combined train and validation sets using the best hyper - parameter set. The performance on the test set has an average Accuracy and F1 scores of 84.84% (SD 2 and 2.08, respectively)

Results

We retained the model providing the highest performance over the 10 runs.