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: ro, split: test'
metrics:
- name: Wer
type: wer
value: 42.218080149114634
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: 0.3430
- Wer: 42.2181
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.396 | 0.9 | 1000 | 0.5565 | 88.6587 |
| 0.187 | 1.8 | 2000 | 0.4436 | 53.4841 |
| 0.0744 | 2.7 | 3000 | 0.3862 | 53.7279 |
| 0.0222 | 3.6 | 4000 | 0.3430 | 42.2181 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.6.1
- Tokenizers 0.15.0