xuliu15/FT-English-10m

Whisper Small English 10m

This model is a fine-tuned version of openai/whisper-small on the Librispeech-English dataset. It achieves the following results on the evaluation set:

• Loss: 0.5626
• Wer: 90.2047

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-07
• 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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4991	66.6667	200	0.7542	98.9448
0.347	133.3333	400	0.6746	98.8666
0.2059	200.0	600	0.6157	97.4288
0.1033	266.6667	800	0.5682	91.1858
0.0885	333.3333	1000	0.5626	90.2047

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1