This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m--concat-->mt5 on the GOOGLE/XTREME_S - MINDS14.EN-US dataset.
It achieves the following results on the evaluation set:
Loss: 0.5685
F1: 0.83333
Accuracy: 0.83258
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 0.0003
train_batch_size: 2
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 8
total_train_batch_size: 32
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
