Masioki
/

fusion_gttbsc_phi-3-best

fusion-cross-attention-sentence-classifier

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Masioki commited on Jun 17

Commit

bd81657

•

1 Parent(s): e5202c5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -37,7 +37,7 @@ ASR encoder: [Whisper small](https://huggingface.co/openai/whisper-small) encode
 Prosody encoder: 2 layer transformer encoder with initial dense projection
 Backbone: [Phi 3 mini](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
 Fusion: 2 residual cross attention fusion layers (F_asr x F_text and F_prosody x F_text) with dense layer on top
-Pooling: Weighted mean
 Multi-label classification head: 2 dense layers with two dropouts 0.3 and Tanh activation inbetween

 Prosody encoder: 2 layer transformer encoder with initial dense projection
 Backbone: [Phi 3 mini](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
 Fusion: 2 residual cross attention fusion layers (F_asr x F_text and F_prosody x F_text) with dense layer on top
+Pooling: Self-attention
 Multi-label classification head: 2 dense layers with two dropouts 0.3 and Tanh activation inbetween