xezpeleta/whisper-small-eu

Whisper Small Basque

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_16_0 eu dataset. It achieves the following results on the evaluation set:

• Loss: 0.1996
• Wer: 12.0128

If you need to use this model with whisper.cpp, you can download the ggml file: ggml-small-eu.bin

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2009	1.04	1000	0.2446	17.6881
0.0759	2.09	2000	0.2102	14.2584
0.0264	3.13	3000	0.2200	13.6898
0.0633	5.02	4000	0.1955	12.5535
0.0199	6.06	5000	0.1996	12.0128

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.8.1.dev0
• Tokenizers 0.13.2