Yassmen/Wav2Vec2_Fine_tuned_on_CremaD_Speech_Emotion_Recognition

Full fine-tune vs jonatasgrosman/wav2vec2-large-xlsr-53-english. Fine-tune: 99% of the weights changed, across 24 of 24 layers.

Tensors changed: Norms 100/114, Attention 192/192, MLP 96/96, Embeddings 2/2, other 2/16

On the Hub · Downloads on Model Pulse