Masioki's picture
Update README.md
bd81657 verified
---
tags:
- generated_from_trainer
model-index:
- name: fusion_gttbsc_phi-3-best
results:
- task:
type: dialogue act classification
dataset:
name: asapp/slue-phase-2
type: hvb
metrics:
- name: F1 macro E2E
type: F1 macro
value: 70.09
- name: F1 macro GT
type: F1 macro
value: 71.86
datasets:
- asapp/slue-phase-2
language:
- en
metrics:
- f1-macro
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# fusion_gttbsc_phi-3-best
Ground truth text with prosody encoding and ASR encoding residual cross attention fusion multi-label DAC
## Model description
ASR encoder: [Whisper small](https://huggingface.co/openai/whisper-small) encoder
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
## Training and evaluation data
Trained on ground truth.
Evaluated on ground truth (GT) and normalized [Whisper small](https://huggingface.co/openai/whisper-small) transcripts (E2E).
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1