metadata
language:
- ro
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Romanian
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Romanian voice 1.0
type: mozilla-foundation/common_voice_11_0
config: ro
split: test
args: 'config: se, split: test'
metrics:
- name: Wer
type: wer
value: 72.18080149114631
Whisper Romanian
This model is a fine-tuned version of openai/whisper-small on the Romanian voice 1.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2682
- Wer: 72.1808
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0756 | 1.8 | 1000 | 0.2180 | 21.3707 |
| 0.0283 | 3.6 | 2000 | 0.2313 | 58.4235 |
| 0.0111 | 5.4 | 3000 | 0.2592 | 41.9923 |
| 0.0066 | 7.19 | 4000 | 0.2682 | 72.1808 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0