arpagon/whisper-tiny-es

Whisper tiny Spanish

This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_11_0 es dataset. It achieves the following results on the evaluation set:

• Loss: 0.4412
• Wer: 21.4074

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: 64
• eval_batch_size: 32
• 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
0.5354	2.01	1000	0.5196	25.5587
0.3328	4.01	2000	0.4889	24.5940
0.4702	6.02	3000	0.4589	22.8354
0.2854	8.02	4000	0.4451	21.6198
0.3537	10.03	5000	0.4412	21.4074

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2