zuazo/whisper-tiny-gl

Whisper Tiny Galician

This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_13_0 gl dataset. It achieves the following results on the evaluation set:

• Loss: 0.5832
• Wer: 26.3504

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: 3.75e-05
• train_batch_size: 256
• eval_batch_size: 128
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0062	19.01	1000	0.5832	26.3504
0.0012	39.01	2000	0.6527	26.7177
0.0006	59.01	3000	0.6950	27.4352
0.0004	79.01	4000	0.7260	28.4044
0.0003	99.01	5000	0.7315	28.1905

Framework versions

• Transformers 4.33.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3