English-2

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

• Loss: 0.0006
• Wer: 68.8034

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	22	0.0837	281.1966
No log	2.0	44	0.0155	174.1453
No log	3.0	66	0.0199	94.4444
No log	4.0	88	0.0067	71.7949
No log	5.0	110	0.0006	68.8034
No log	6.0	132	0.0006	68.8034
No log	7.0	154	0.0006	68.8034
No log	8.0	176	0.0006	68.8034
No log	9.0	198	0.0006	68.8034
No log	10.0	220	0.0006	68.8034

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.13.3