Baseline openai/whisper-tiny on Greek. Evaluated on 1701 audio samples
This is a report for the baseline (no finetuning) openai/whisper-tiny on the mozilla-foundation/common_voice_17_0- Greek dataset. It achieves the following results on the evaluation set:
- eval_loss: 1.5188
- eval_model_preparation_time: 0.0016
- eval_wer: 79.1941
- eval_runtime: 320.04
- eval_samples_per_second: 5.315
- eval_steps_per_second: 0.666
- step: 0
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: 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: 0
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for kostissz/whisper-tiny-el-baseline
Base model
openai/whisper-tiny