imascslr_openslr_festfox

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: 0.0625
• Wer: 32.6698

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: 1000
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0802	0.41	1000	0.1407	58.6713
0.0482	0.82	2000	0.0868	43.0953
0.0259	1.23	3000	0.0714	36.0040
0.0181	1.64	4000	0.0625	32.6698

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1