akashshrm5/whisper-small-hi

Whisper Small Hi - akash_sharma_test

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: 0.9705
• Wer: 58.4416

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: 1
• eval_batch_size: 1
• 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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0021	20.0	1000	0.8610	61.0390
0.0	40.0	2000	0.9097	59.7403
0.0	60.0	3000	0.9417	59.7403
0.0	80.0	4000	0.9622	59.7403
0.0	100.0	5000	0.9705	58.4416

Framework versions

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