akera/ultravox-salt-asr-v3

ultravox-salt-asr

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

• Loss: 6.8589

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
13.9537	1.6595	250	2.0715
4.2504	3.3131	500	2.7861
2.8991	4.9725	750	3.0254
1.5076	6.6261	1000	3.8784
1.0628	8.2798	1250	3.8000
1.155	9.9392	1500	3.9960
0.8838	11.5928	1750	4.3552
0.6662	13.2465	2000	4.4795
0.709	14.9059	2250	4.9650
0.5234	16.5595	2500	6.0853
0.3858	18.2132	2750	6.3153
0.3536	19.8726	3000	6.8589

Framework versions

• Transformers 4.54.0
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2