Whisper-Small-TF-TIMIT-FLEUR

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: 0.8885
• Wer: 35.0461

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: 6.25e-06
• 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: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4965	1.27	500	0.9304	37.3857
0.1668	2.54	1000	0.8561	32.7384
0.069	3.81	1500	0.8093	52.7441
0.0152	5.08	2000	0.9021	54.9437
0.0083	6.35	2500	0.8471	57.3611
0.0021	7.61	3000	0.8885	35.0461

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 1.13.0
• Datasets 2.1.0
• Tokenizers 0.13.2