Timit_Exp – AI Model by TartaYug | AlphaNeural AI | AlphaNeural AI

You can deploy this model and start earning money today!

TartaYug/
Timit_Exp

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-base

endpoints_compatible

Views

No views yet

Timit_Exp

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

Loss: nan
Wer: 1.0

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
7.9059	3.4483	500	nan	1.0
0.0	6.8966	1000	nan	1.0
0.0	10.3448	1500	nan	1.0
0.0	13.7931	2000	nan	1.0
0.0	17.2414	2500	nan	1.0
0.0	20.6897	3000	nan	1.0
0.0	24.1379	3500	nan	1.0
0.0	27.5862	4000	nan	1.0

Framework versions

Transformers 4.45.0
Pytorch 2.3.1
Datasets 2.15.0
Tokenizers 0.20.0