W2v Speech Emotion Recognition

🚀 Wav2Vec2 Speech Emotion Recognition for English

This model leverages the Wav2Vec2 architecture to recognize emotions in English speech. It can detect a range of emotions, offering valuable insights into the emotional tone of spoken English.

🚀 Quick Start

To use this model, you first need to install the necessary packages. Then, you can load the model and perform emotion classification on an English audio file.

Installation

pip install transformers
pip install torchaudio

Example Usage

from transformers import pipeline

# Load the fine-tuned model and feature extractor
pipe = pipeline("audio-classification", model="Khoa/w2v-speech-emotion-recognition")

# Path to your audio file
audio_file = "path_to_your_audio_file.wav"

# Perform emotion classification
predictions = pipe(audio_file)

# Map predictions to real emotion labels
label_map = {
    "LABEL_0": "sadness",
    "LABEL_1": "angry",
    "LABEL_2": "disgust",
    "LABEL_3": "fear",
    "LABEL_4": "happy",
    "LABEL_5": "neutral"
}

# Convert predictions to readable labels
mapped_predictions = [
    {"score": pred["score"], "label": label_map[pred["label"]]} 
    for pred in predictions
]

# Display results
print(mapped_predictions)

✨ Features

• Emotion Detection: Capable of detecting multiple emotions including sadness, anger, disgust, fear, happiness, and neutral in English speech.
• Fine - tuned Model: Fine - tuned on a high - quality dataset for better performance in emotion recognition tasks.

📦 Model Details

🔧 Technical Details

The model was fine - tuned on the Speech Emotion Recognition Dataset, using the Wav2Vec2 architecture. The training process involved multiple epochs with a learning rate of 1e - 5.

📚 Documentation

Training Results

The model achieved the following results on the test set:

Test Accuracy: 0.7435

Classification Report:

              precision    recall  f1-score   support

     sadness       0.68      0.71      0.70       251
       angry       0.75      0.93      0.83       258
     disgust       0.86      0.64      0.73       250
        fear       0.75      0.61      0.67       287
       happy       0.73      0.68      0.71       231
     neutral       0.72      0.92      0.81       212

    accuracy                           0.74      1489
   macro avg       0.75      0.75      0.74      1489
weighted avg       0.75      0.74      0.74      1489

Example Output

[
    {"score": 0.95, "label": "angry"},
    {"score": 0.02, "label": "happy"},
    {"score": 0.01, "label": "disgust"},
    {"score": 0.01, "label": "neutral"},
    {"score": 0.01, "label": "fear"}
]

📄 License

This model is released under the MIT license.

⚠️ Important Note

This model is specifically trained on English speech data and may not perform well on other languages or dialects. Additionally, as with any machine learning model, there may be biases present in the training data that could affect the model's predictions.