whisper-tiny-sinhala-20k-8k-steps-v2

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

• Loss: 0.1889
• Wer: 51.6357

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.213	0.53	1000	0.2200	57.9731
0.1611	1.07	2000	0.2017	54.4777
0.1601	1.6	3000	0.1942	53.3355
0.1384	2.13	4000	0.1913	52.2206
0.1101	2.67	5000	0.1889	51.6357

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.15.0