Speech Emotion Recognition By Fine Tuning Wav2Vec 2.0 The model is a fine tuned version of jonatasgrosman/wav2vec2 large xlsr 53 english for a Speech Emotion Recognition (SER) task. Several datasets were used the fine tune the original model: Surrey Audio Visual Expressed Emotion (SAVEE) 480 audio files from 4 male actors Ryerson Audio Visual Database of Emotional Speech and Song (RAVDESS) 1440 audio files from 24 professional actors (12 female, 12 male) Toronto emotional speech set (TESS) 2800 audio files from 2 female actors 7 labels/emotions were used as classification labels It achieves the following results on the evaluation set: Loss: 0.104075 Accuracy: 0.97463 Model Usage Training procedure Training hyperparameters The following hyperparameters were used during training: learning rate: 0.0001 train batch size: 4 eval batch size: 4 eval steps: 500 seed: 42 gradient accumulation steps: 2 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e 08 num epochs: 4 max steps=7500 save steps: 1500 Training results Step Training Loss Validation Loss Accuracy 500 1.8124 1.365212 0.486258 1000 0.8872 0.773145 0.79704 1500 0.7035 0.574954 0.852008 2000 0.6879 1.286738 0.775899 2500 0.6498…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy