You can deploy this model and start earning money today!

Masioki/
enc-gttbsc_phi-3-freezed

transformers

tensorboard

safetensors

cross-attention-sentence-classifier

generated_from_trainer

asapp/slue-phase-2

model-index

endpoints_compatible

Views

No views yet

enc-gttbsc_phi-3-freezed

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

Model description

ASR encoder: Whisper small encoder
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: 0.0002
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

Masioki/enc-gttbsc_phi-3-freezed