ap-1Un7Xp3v0KIWWN5mhtAYUM – AI Model by charlesfrye | AlphaNeural AI

You can deploy this model and start earning money today!

charlesfrye/
ap-1Un7Xp3v0KIWWN5mhtAYUM

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-large-v3

endpoints_compatible

Views

No views yet

ap-1Un7Xp3v0KIWWN5mhtAYUM

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4934
Model Preparation Time: 0.0218
Wer: 0.1568

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: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
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: 400
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Wer
0.2529	0.9791	41	0.2883	0.0218	0.1136
0.1893	1.9791	82	0.3071	0.0218	0.1172
0.1213	2.9791	123	0.4629	0.0218	0.1244
0.1144	3.9791	164	0.4764	0.0218	0.1537
0.1143	4.9791	205	0.4934	0.0218	0.1568

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0