whisper-small-hi

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: 1.1846
• Wer: 100.2053

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: 500
• training_steps: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	2.5	10	2.4583	101.2320
No log	5.0	20	1.9956	98.0493
2.3242	7.5	30	1.5232	96.5092
2.3242	10.0	40	1.1846	100.2053

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cpu
• Datasets 2.9.0
• Tokenizers 0.13.2