jayavardhan31/whisper-base-speech

Whisper base te - jayavardhan

This model is a fine-tuned version of openai/whisper-base on the fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.1934
• Wer: 70.4367

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 250
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.084	6.12	500	0.1455	71.1065
0.0297	12.23	1000	0.1682	69.8570
0.0175	18.35	1500	0.1934	70.4367

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2