metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- fleurs
metrics:
- wer
model-index:
- name: whisper-large-v2-greek
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: fleurs
type: fleurs
config: el_gr
split: test
args: el_gr
metrics:
- name: Wer
type: wer
value: 0.8398897182435613
whisper-large-v2-greek
This model is a fine-tuned version of openai/whisper-large-v2 on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2442
- Wer Ortho: 0.8376
- Wer: 0.8399
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.1502 | 1.0 | 217 | 0.1780 | 1.1731 | 1.1960 |
| 0.0608 | 2.0 | 435 | 0.1869 | 1.1069 | 1.1209 |
| 0.0305 | 3.0 | 653 | 0.2029 | 1.1970 | 1.2144 |
| 0.0178 | 4.0 | 871 | 0.2186 | 1.3240 | 1.3458 |
| 0.0108 | 5.0 | 1088 | 0.2253 | 1.1080 | 1.1200 |
| 0.0076 | 6.0 | 1306 | 0.2301 | 1.0047 | 1.0155 |
| 0.0072 | 7.0 | 1524 | 0.2402 | 1.1153 | 1.1405 |
| 0.0051 | 8.0 | 1742 | 0.2434 | 1.0095 | 1.0264 |
| 0.0056 | 8.97 | 1953 | 0.2442 | 0.8376 | 0.8399 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3