fineturning-with-pretraining-3 – AI Model by Aviral2412 | AlphaNeural AI

You can deploy this model and start earning money today!

Aviral2412/
fineturning-with-pretraining-3

like

0

automatic-speech-recognition

generated_from_trainer

common_voice_1_0

Aviral2412/mini_model

endpoints_compatible

Views

No views yet

fineturning-with-pretraining-3

This model is a fine-tuned version of Aviral2412/mini_model on the common_voice_1_0 dataset. It achieves the following results on the evaluation set:

Loss: 2.9160
Wer: 1.0000

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: 0.0001
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.0042	4.27	500	3.1928	1.0000
2.9673	8.55	1000	3.0856	1.0000
2.9929	12.82	1500	3.0173	1.0000
2.9458	17.09	2000	2.9282	1.0000
2.9084	21.37	2500	2.9734	1.0000
2.8651	25.64	3000	2.9234	1.0000
2.8307	29.91	3500	2.9160	1.0000

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2