You can deploy this model and start earning money today!

Masioki/
prosody_gtsc_phi-3-mini

Name: prosody_gtsc_phi-3-mini
Availability: InStock

transformers

tensorboard

safetensors

cross-attention-sentence-classifier

generated_from_trainer

asapp/slue-phase-2

model-index

endpoints_compatible

Views

No views yet

prosody_gtsc_phi-3-mini

Ground truth text with prosody encoding residual cross attention multi-label DAC

Model description

Prosody encoder: 2 layer transformer encoder with initial dense projection
Backbone: Phi 3 mini
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 transcripts (E2E).

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0005
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 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1

Masioki/prosody_gtsc_phi-3-mini