---
license: apache-2.0
datasets:
- KELONMYOSA/dusha_emotion_audio
language:
- ru
pipeline_tag: audio-classification
metrics:
- accuracy
widget:
- example_title: Emotion - "Neurtal"
  src: https://huggingface.co/KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru/resolve/main/neutral.mp3
- example_title: Emotion - "Positive"
  src: https://huggingface.co/KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru/resolve/main/positive.mp3
- example_title: Emotion - "Angry"
  src: https://huggingface.co/KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru/resolve/main/angry.mp3
- example_title: Emotion - "Sad"
  src: https://huggingface.co/KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru/resolve/main/sad.mp3
- example_title: Emotion - "Other"
  src: https://huggingface.co/KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru/resolve/main/other.mp3
---

# Speech Emotion Recognition

The model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) for a Speech Emotion Recognition (SER) task.

The dataset used to fine-tune the original pre-trained model is the [DUSHA dataset](https://huggingface.co/datasets/KELONMYOSA/dusha_emotion_audio). The dataset consists of about 125 000 audio recordings in Russian with four basic emotions that usually appear in a dialog with a virtual assistant: Happiness (Positive), Sadness, Anger and Neutral emotion.

```python
emotions = ['neutral', 'positive', 'angry', 'sad', 'other']
```

# How to use

```python
from transformers.pipelines import pipeline

pipe = pipeline(model="KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru", trust_remote_code=True)

result = pipe("speech.wav")
print(result)
```
~~~
[{'label': 'neutral', 'score': 0.00318}, {'label': 'positive', 'score': 0.00376}, {'label': 'sad', 'score': 0.00145}, {'label': 'angry', 'score': 0.98984}, {'label': 'other', 'score': 0.00176}]
~~~

# Evaluation

It achieves the following results:
- Training Loss: 0.528700
- Validation Loss: 0.349617
- Accuracy: 0.901369