Pageee/FT-English-10mb

Whisper-Small En-10m

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

• Loss: 0.2180
• Wer: 4.2581

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 300
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0142	18.1818	100	0.2208	4.0237
0.0005	36.3636	200	0.2145	4.1583
0.0002	54.5455	300	0.2162	4.2214
0.0001	72.7273	400	0.2175	4.2418
0.0001	90.9091	500	0.2180	4.2581

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1