whisper-medium-ro

This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1812
• Wer: 99.5018

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0777	1.8	1000	0.1651	100.1685
0.024	3.6	2000	0.1634	99.8853
0.0039	5.4	3000	0.1734	99.5484
0.001	7.19	4000	0.1812	99.5018

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.1
• Datasets 2.16.0
• Tokenizers 0.15.0