whisper2

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

• Loss: 0.2574
• Wer: 96.9001

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: 2
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• 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
0.1143	1.27	1000	0.2184	56.9383
0.0524	2.54	2000	0.2134	54.9835
0.024	3.82	3000	0.2309	61.1703
0.0076	5.09	4000	0.2574	96.9001

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1