YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MannMitra Fine-tuned Speech Emotion Model

Wav2Vec2ForSequenceClassification fine-tuned on the 7 supported RAVDESS speech-emotion classes. This package is prepared for Hugging Face Hub upload; it has not been uploaded.

Labels:

0 angry 1 calm 2 disgust 3 fearful 4 happy 5 sad 6 surprised

Expected input is mono float audio sampled at 16 kHz through the bundled Wav2Vec2Processor. The model weights and configuration are copied unchanged from the active best checkpoint.

Downloads last month
12
Safetensors
Model size
94.6M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support