This model is a fine-tuned version of openai/whisper-Medium on the 10 hrs of Catalan Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
eval_loss: 4.9217
eval_wer: 132.1947
eval_runtime: 3848.0596
eval_samples_per_second: 0.78
eval_steps_per_second: 0.78
epoch: 1.14
step: 2000
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: 0.001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
