whisper-tiny-ASR

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: 0.8363
• Wer: 60.1936

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: 32
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1494	6.8	1000	0.4732	50.4342
0.0113	13.61	2000	0.6944	62.9461
0.0024	20.41	3000	0.8042	59.8032
0.0014	27.21	4000	0.8363	60.1936

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1