metadata

license: mit
language:
  - en
pipeline_tag: audio-classification
tags:
  - wavlm
  - msp-podcast
  - emotion-recognition
  - audio
  - speech
  - valence
  - arousal
  - dominance
  - lucas
  - speech-emotion-recognition

The model was trained on MSP-Podcast for the Odyssey 2024 Emotion Recognition competition baseline
This particular model is the multi-attributed based model which predict arousal, dominance and valence in a range of approximately 0...1.

Benchmarks

CCC based on test3 and Development sets of the Odyssey Competition

Multi-Task Setup
Test 3			Development
Val	Dom	Aro	Val	Dom	Aro
0.577	0.577	0.405	0.652	0.688	0.579

For more details: demo, paper/soon and GitHub.

@InProceedings{Goncalves_2024,
            author={L. Goncalves and A. N. Salman and A. {Reddy Naini} and L. Moro-Velazquez and T. Thebaud and L. {Paola Garcia} and N. Dehak and B. Sisman and C. Busso},
            title={Odyssey2024 - Speech Emotion Recognition Challenge: Dataset, Baseline Framework, and Results},
            booktitle={Odyssey 2024: The Speaker and Language Recognition Workshop)},
            volume={To appear},
            year={2024},
            month={June},
            address =  {Quebec, Canada},
}

Usage

from transformers import AutoModelForAudioClassification
import librosa, torch

#load model
model = AutoModelForAudioClassification.from_pretrained("3loi/SER-Odyssey-Baseline-WavLM-Multi-Attributes", trust_remote_code=True)

#get mean/std
mean = model.config.mean
std = model.config.std


#load an audio file
audio_path = "/path/to/audio.wav"
raw_wav, _ = librosa.load(audio_path, sr=model.config.sampling_rate)

#normalize the audio by mean/std
norm_wav = (raw_wav - mean) / (std+0.000001)

#generate the mask
mask = torch.ones(1, len(norm_wav))

#batch it (add dim)
wavs = torch.tensor(norm_wav).unsqueeze(0)


#predict
with torch.no_grad():
    pred = model(wavs, mask)

print(model.config.id2label) 
print(pred)
#{0: 'arousal', 1: 'dominance', 2: 'valence'}
#tensor([[0.3670, 0.4553, 0.4240]])