metadata
base_model: openai/whisper-base
datasets:
- fleurs
language:
- it
license: apache-2.0
metrics:
- wer
tags:
- hf-asr-leaderboard
- generated_from_trainer
model-index:
- name: Whisper Tiny Itlian - Chee Li
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Google Fleurs
type: fleurs
config: it_it
split: None
args: 'config: it split: test'
metrics:
- type: wer
value: 28.895899053627762
name: Wer
Whisper Tiny Itlian - Chee Li
This model is a fine-tuned version of openai/whisper-base on the Google Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.5007
- Wer: 28.8959
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0648 | 4.6729 | 1000 | 0.3617 | 28.7455 |
| 0.0048 | 9.3458 | 2000 | 0.4424 | 26.5858 |
| 0.0025 | 14.0187 | 3000 | 0.4710 | 28.1291 |
| 0.0016 | 18.6916 | 4000 | 0.4928 | 28.2601 |
| 0.0013 | 23.3645 | 5000 | 0.5007 | 28.8959 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1