You can deploy this model and start earning money today!

Badri0510/
whisper-tanglish-100hr-production

Name: whisper-tanglish-100hr-production
Availability: InStock

Views

No views yet

whisper-tanglish-100hr-production

This model is a fine-tuned version of Badri0510/whisper-tanglish-voice-generalized-5000 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: 5e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
training_steps: 10000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.0012	0.05	500	0.4384	0.5265
0.0024	1.011	1000	0.4401	0.5236
0.0019	1.061	1500	0.4440	0.5293
0.0034	2.0211	2000	0.4404	0.5237
0.0017	2.0711	2500	0.4505	0.5260
0.0051	3.0316	3000	0.4458	0.5283
0.0039	3.0816	3500	0.4464	0.5243