JulieHinge/whisper-medium-ftspeech

Whisper tiny FTSpeech - Julie

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

• Loss: 0.6006
• Wer: 97.1761

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: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9429	0.0080	500	0.9411	87.9967
0.7782	0.0161	1000	0.7891	91.5049
0.7176	0.0241	1500	0.7164	89.9351
0.6545	0.0321	2000	0.6686	85.8745
0.6171	0.0402	2500	0.6395	91.9062
0.5767	0.0482	3000	0.6176	94.2052
0.546	0.0562	3500	0.6006	97.1761

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.21.0