uaspeech-large-finetune-long-evals-30-11-8AM – AI Model by neuronbit | AlphaNeural AI

You can deploy this model and start earning money today!

neuronbit/
uaspeech-large-finetune-long-evals-30-11-8AM

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-large-v3

endpoints_compatible

Views

No views yet

Visualize in Weights & Biases

uaspeech-large-finetune-long-evals-30-11-8AM

This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3451

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: 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
0.2274	0.2070	500	0.3534
0.124	0.4139	1000	0.3163
0.078	0.6209	1500	0.3397
0.0541	0.8278	2000	0.3277
0.0318	1.0348	2500	0.3360
0.0154	1.2417	3000	0.3171
0.0058	1.4487	3500	0.3465
0.0082	1.6556	4000	0.3501
0.0086	1.8626	4500	0.3507
0.0046	2.0695	5000	0.3451

Framework versions

Transformers 4.45.2
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3