You can deploy this model and start earning money today!

Masioki/
prosody_gttbsc_distilbert-uncased-best

Name: prosody_gttbsc_distilbert-uncased-best
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_gttbsc_distilbert-uncased-best

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

Model description

Prosody encoder: 2 layer transformer encoder with initial dense projection Backbone: DistilBert uncased
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 slue-phase-2 hvb.
Evaluated on ground truth (GT) and normalized Whisper small transcripts (E2E).

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0004
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_gttbsc_distilbert-uncased-best