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-sm-el-intlv-xl
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0
type: mozilla-foundation/common_voice_11_0
config: el
split: test
metrics:
- name: Wer
type: wer
value: 20.468053491827636
whisper-sm-el-intlv-xl
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0,google/fleurs el,el_gr dataset. It achieves the following results on the evaluation set:
- Loss: 0.4528
- Wer: 20.4681
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: 6.25e-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.0705 | 2.49 | 1000 | 0.2870 | 21.4989 |
| 0.0147 | 4.98 | 2000 | 0.3689 | 21.0160 |
| 0.0024 | 7.46 | 3000 | 0.4156 | 20.7559 |
| 0.0014 | 9.95 | 4000 | 0.4423 | 20.7002 |
| 0.0011 | 12.44 | 5000 | 0.4528 | 20.4681 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0
- Datasets 2.7.1.dev0
- Tokenizers 0.12.1