TheRains/output-tiny-id

Whisper tiny ID - Augmented

This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_12_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2874
• Wer: 14.4271

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6729	0.77	200	0.4170	21.8473
0.5012	1.54	400	0.3465	18.2560
0.3832	2.31	600	0.3097	16.0971
0.2853	3.07	800	0.2970	14.3180
0.2416	3.84	1000	0.2874	14.4271

Framework versions

• Transformers 4.29.0.dev0
• Pytorch 2.0.0+cu117
• Datasets 2.10.1
• Tokenizers 0.13.2