IoanaLiviaPopescu/IoanaLiviaPopescu/real-data-synth-data-1600-1-Standard-B-whisper-small-v0

This model is a fine-tuned version of openai/whisper-small on the IoanaLiviaPopescu/RealVoiceSynthVoice-1600-1-Standard-B dataset. It achieves the following results on the evaluation set:

• Loss: 0.3743
• Wer: 17.3336

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: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0	0	0.6024	27.8812
0.271	1.0	63	0.3957	18.8272
0.1077	2.0	126	0.3686	17.4258
0.0594	3.0	189	0.3743	17.3336
0.0356	4.0	252	0.3941	17.5364
0.0253	5.0	315	0.4027	17.4995

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1