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 small Greek Farsipal and 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: el
split: None
metrics:
- name: Wer
type: wer
value: 16.50260029717682
Whisper small Greek Farsipal and El Greco
This model is a fine-tuned version of emilios/whisper-sm-farsipal-e7 on the mozilla-foundation/common_voice_11_0,google/fleurs el,el_gr dataset. It achieves the following results on the evaluation set:
- Loss: 0.5015
- Wer: 16.5026
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: 3e-09
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0002 | 2.49 | 1000 | 0.5015 | 16.5212 |
| 0.0002 | 4.98 | 2000 | 0.5015 | 16.5119 |
| 0.0002 | 7.46 | 3000 | 0.5015 | 16.5397 |
| 0.0002 | 9.95 | 4000 | 0.5015 | 16.5397 |
| 0.0002 | 12.44 | 5000 | 0.5015 | 16.5583 |
| 0.0002 | 14.93 | 6000 | 0.5015 | 16.5769 |
| 0.0002 | 17.41 | 7000 | 0.5015 | 16.5397 |
| 0.0002 | 19.9 | 8000 | 0.5015 | 16.5026 |
| 0.0002 | 22.39 | 9000 | 0.5015 | 16.5212 |
| 0.0002 | 24.88 | 10000 | 0.5020 | 16.5583 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 2.0.0.dev20221216+cu116
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2