You can deploy this model and start earning money today!

akera/
ultravox-qwen-salt-asr

Name: ultravox-qwen-salt-asr
Availability: InStock

Views

No views yet

ultravox-qwen-salt-asr

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

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
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: cosine
lr_scheduler_warmup_steps: 500
num_epochs: 2

Training Loss	Epoch	Step	Validation Loss
2.5509	0.1665	25	2.3925
2.2932	0.3331	50	2.2540
2.162	0.4996	75	2.1993
2.1344	0.6661	100	2.1686
2.0795	0.8326	125	2.1328
2.0711	0.9992	150	2.1107
2.0117	1.1599	175	2.0695
1.9667	1.3264	200	2.0217
1.9706	1.4929	225	1.9879
1.8503	1.6595	250	1.9367
1.8512	1.8260	275	1.9007
1.7906	1.9925	300	1.8666