kalschi/whisper-small-hi

kalschi-whisper-small

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3033
• Wer: 38.4661

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: 50
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4916	0.24	100	0.5362	46.4404
0.2707	0.49	200	0.3474	42.0384
0.23	0.73	300	0.3133	38.8597
0.2213	0.98	400	0.3033	38.4661

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2