zuazo/whisper-base-gl

Whisper Base Galician

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

• Loss: 0.4754
• Wer: 18.6879

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: 2.5e-05
• train_batch_size: 128
• eval_batch_size: 64
• 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
0.0088	9.02	1000	0.4219	18.7776
0.0015	19.02	2000	0.4754	18.6879
0.0008	29.02	3000	0.5036	18.9000
0.0005	39.02	4000	0.5225	19.0553
0.0004	49.02	5000	0.5307	19.1122

Framework versions

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