iPr0x/whisper-small-hi

Whisper Small Hi - Prox

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4138
• Wer: 32.2746

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0823	2.36	1000	0.2898	34.5522
0.0214	4.73	2000	0.3268	33.1567
0.0027	7.09	3000	0.3842	32.4196
0.0005	9.46	4000	0.4138	32.2746

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2