wav2vec2-large-xlsr-timit-demo-maf – AI Model by mafari2025 | AlphaNeural AI

You can deploy this model and start earning money today!

mafari2025/
wav2vec2-large-xlsr-timit-demo-maf

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-base

endpoints_compatible

Views

No views yet

wav2vec2-large-xlsr-timit-demo-maf

This model is a fine-tuned version of facebook/wav2vec2-base on the timit_asr dataset. It achieves the following results on the evaluation set:

Loss: 0.4095
Wer: 0.2746

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: 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: 1000
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.5007	3.4483	500	1.1214	0.7809
0.5442	6.8966	1000	0.3970	0.3577
0.2007	10.3448	1500	0.3964	0.3198
0.1178	13.7931	2000	0.3452	0.2970
0.0808	17.2414	2500	0.4296	0.2957
0.0606	20.6897	3000	0.3997	0.2883
0.0467	24.1379	3500	0.4128	0.2791
0.0393	27.5862	4000	0.4095	0.2746

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0