metadata
language:
- el
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0,google/fleurs
metrics:
- wer
model-index:
- name: Whisper Medium El Greco
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0,google/fleurs el,el_gr
type: mozilla-foundation/common_voice_11_0,google/fleurs
config: null
split: None
metrics:
- name: Wer
type: wer
value: 11.199851411589897
Whisper Medium El Greco
This model is a fine-tuned version of emilios/whisper-medium-el on the mozilla-foundation/common_voice_11_0,google/fleurs el,el_gr dataset. It achieves the following results on the evaluation set:
- Loss: 0.3801
- Wer: 11.1999
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 |
|---|---|---|---|---|
| 0.0176 | 2.49 | 1000 | 0.2945 | 12.6114 |
| 0.0064 | 4.98 | 2000 | 0.3423 | 12.2307 |
| 0.0022 | 7.46 | 3000 | 0.3632 | 11.5899 |
| 0.0014 | 9.95 | 4000 | 0.3788 | 11.2556 |
| 0.0008 | 12.44 | 5000 | 0.3801 | 11.1999 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2