You can deploy this model and start earning money today!

colorlessideas/
xlsr-toratan-240-copt-120

Name: xlsr-toratan-240-copt-120
Availability: InStock

automatic-speech-recognition

generated_from_trainer

colorlessideas/xlsr-toratan-240-copt

finetune

apache-2.0

endpoints_compatible

Views

No views yet

xlsr-toratan-240-copt-120

This model is a fine-tuned version of colorlessideas/xlsr-toratan-240-copt on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0132
Cer: 0.0032

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: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: 500
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
4.3453	4.1667	400	1.9323	0.5521
1.573	8.3333	800	0.8279	0.2562
0.953	12.5	1200	0.3825	0.1332
0.6032	16.6667	1600	0.1430	0.0577
0.3933	20.8333	2000	0.0524	0.0163
0.2911	25.0	2400	0.0192	0.0055
0.2163	29.1667	2800	0.0132	0.0032

Framework versions

Transformers 4.50.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0

colorlessideas/xlsr-toratan-240-copt-120

xlsr-toratan-240-copt-120

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

colorlessideas/
xlsr-toratan-240-copt-120