whisper-tiny-full-data-language-v1-20ep

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: 0.2277

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: 0.00015
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• distributed_type: tpu
• num_devices: 8
• total_train_batch_size: 256
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5000
• training_steps: 63840

Training results

Training Loss	Epoch	Step	Validation Loss
0.3592	1.57	5000	0.5930
0.244	3.13	10000	0.4584
0.2032	4.7	15000	0.3970
0.1737	6.27	20000	0.3599
0.1531	7.83	25000	0.3304
0.1299	9.4	30000	0.3080
0.1232	10.96	35000	0.2872
0.1023	12.53	40000	0.2749
0.0863	14.1	45000	0.2589
0.0773	15.66	50000	0.2489
0.0648	17.23	55000	0.2387
0.0572	18.8	60000	0.2304

Framework versions

• Transformers 4.28.1
• Pytorch 2.1.0a0+gitcc01568
• Datasets 2.13.1
• Tokenizers 0.13.3