metadata
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: whisper-large-v3-croarian_10
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audiofolder
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Wer
type: wer
value: 91.75156739811912
whisper-large-v3-croarian_10
This model is a fine-tuned version of openai/whisper-large-v3 on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.1025
- Wer: 91.7516
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: 16
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0795 | 10.87 | 1000 | 1.6251 | 88.0094 |
| 0.0162 | 21.74 | 2000 | 1.8668 | 126.1658 |
| 0.0066 | 32.61 | 3000 | 2.0541 | 104.8295 |
| 0.0042 | 43.48 | 4000 | 2.1025 | 91.7516 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1