whisper-tiny-fluers_V2_telugu_Augmentation_bf16

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5041
• Wer: 60.0

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: 1.5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0846	2.72	300	0.3169	83.05
0.065	5.44	600	0.3526	68.65
0.0379	8.15	900	0.3954	65.75
0.0253	10.9	1200	0.4391	62.9500
0.0147	13.62	1500	0.4715	59.0500
0.0094	16.35	1800	0.5041	60.0

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 1.12.1
• Datasets 2.11.0
• Tokenizers 0.13.3