---
license: mit
base_model:
- audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim
pipeline_tag: audio-classification
tags:
- emotion
- '"happy", "angry", "sad", "scared", "neutral"'
---

This is the model used in the papers
* N. Mousavi and F. Burkhardt: The Emotional Portrayal of an Ordinary Talk, Proc. ESSV 2026
* Mousavi, Burkhardt and Schuller: Modeling Emotion in German Ordinary Speech, to be published

We used the embeddings of a transformer model that give emotional dimension values (trained on MSPPodcast: [audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim](https://huggingface.co/audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim))
to train a Multi Layer Perceptron with layers = [1024, 64] , default learning rate (.0001) and Adam optimizer, no dropout, patience set to 10.

With the [nkululeko framework](https://github.com/felixbur/nkululeko)
Training data was the test set of [Berlin Emodb](https://zenodo.org/records/17651657) and the whole of [Italian Emovo](https://aclanthology.org/L14-1478/) database,
for classification from audio to ["happy", "angry", "sad", "scared", "neutral"].
Cross-domain evaluation with [Ravdess database](https://zenodo.org/records/1188976), without the songs, resulted in .561 UAR

Here's the screenshot of this outcome:
![image](https://cdn-uploads.huggingface.co/production/uploads/60b27cf62639a4cde57f57a0/sB08yfegzEn6UK8TAdZ-P.png)

We attach a test_model.py script to this model, so you should be able to try it yourself:

```
Usage: test_model.py [OPTIONS] MODEL AUDIO

  Predict emotion from an audio file using a nkululeko MLP + audwav2vec2
  model.

  MODEL  Path to the .model file (torch state dict saved by nkululeko).
  AUDIO  Path to the audio file (must be 16 kHz mono WAV).

  Example:
    uv run test_model.py my_experiment_0_011.model sample.wav
    uv run test_model.py my_experiment_0_011.model sample.wav --w2v2-root /data/audmodel/

Options:
  --w2v2-root DIR  Directory where the w2v2 onnx model is cached or will be
                   downloaded to.  [default: ./audmodel/]
  -h, --help       Show this message and exit.

```