metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: whisper-small-el
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: el
          split: None
          args: el
        metrics:
          - name: Wer
            type: wer
            value: 30.64381658175081

whisper-small-el

This model is a fine-tuned version of openai/whisper-small on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.3865
Model Preparation Time: 0.0041
Wer: 30.6438

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: 24
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
training_steps: 2000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Wer
0.5511	0.3311	50	0.3685	0.0041	39.3516
0.3132	0.6623	100	0.3168	0.0041	35.6276
0.2709	0.9934	150	0.2897	0.0041	33.4785
0.1634	1.3245	200	0.2829	0.0041	33.1450
0.1551	1.6556	250	0.2746	0.0041	32.5614
0.1559	1.9868	300	0.2683	0.0041	31.8481
0.0818	2.3179	350	0.2735	0.0041	31.3942
0.0808	2.6490	400	0.2735	0.0041	31.9592
0.0799	2.9801	450	0.2765	0.0041	32.4595
0.0451	3.3113	500	0.2922	0.0041	31.4590
0.0436	3.6424	550	0.2892	0.0041	31.0514
0.0436	3.9735	600	0.2902	0.0041	31.3942
0.0241	4.3046	650	0.3117	0.0041	31.2552
0.0212	4.6358	700	0.3162	0.0041	31.0699
0.0226	4.9669	750	0.3172	0.0041	30.8754
0.0127	5.2980	800	0.3521	0.0041	32.5336
0.0125	5.6291	850	0.3432	0.0041	31.1996
0.0123	5.9603	900	0.3463	0.0041	31.4034
0.0077	6.2914	950	0.3764	0.0041	31.0699
0.0071	6.6225	1000	0.3607	0.0041	32.4317
0.0062	6.9536	1050	0.3698	0.0041	30.8754
0.0045	7.2848	1100	0.3758	0.0041	30.9588
0.0035	7.6159	1150	0.3865	0.0041	30.6438
0.0038	7.9470	1200	0.3856	0.0041	31.2830
0.0027	8.2781	1250	0.3800	0.0041	30.8569
0.0021	8.6093	1300	0.3858	0.0041	30.6901
0.0022	8.9404	1350	0.3949	0.0041	31.1996
0.0017	9.2715	1400	0.4020	0.0041	30.7920
0.0016	9.6026	1450	0.4061	0.0041	30.9588
0.0016	9.9338	1500	0.4111	0.0041	31.0514
0.0014	10.2649	1550	0.4067	0.0041	31.1996
0.0013	10.5960	1600	0.4093	0.0041	31.0144
0.0013	10.9272	1650	0.4112	0.0041	30.8661
0.0012	11.2583	1700	0.4126	0.0041	30.9680
0.0012	11.5894	1750	0.4134	0.0041	30.9588
0.0012	11.9205	1800	0.4145	0.0041	30.9217
0.0011	12.2517	1850	0.4155	0.0041	30.8384
0.0011	12.5828	1900	0.4160	0.0041	30.8939
0.0011	12.9139	1950	0.4163	0.0041	30.8754
0.0011	13.2450	2000	0.4164	0.0041	30.8754

Framework versions

Transformers 4.48.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0