metadata
language:
- it
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper small it - m1
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: fleurs
type: google/fleurs
config: it_it
split: None
args: 'config: it_it, split: test, train'
metrics:
- name: Wer
type: wer
value: 8.1873331715603
Whisper small it - m1
This model is a fine-tuned version of openai/whisper-small on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2185
- Wer: 8.1873
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: 2500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0744 | 2.6316 | 500 | 0.1838 | 10.7450 |
| 0.006 | 5.2632 | 1000 | 0.2006 | 8.1145 |
| 0.0022 | 7.8947 | 1500 | 0.2094 | 8.0951 |
| 0.0017 | 10.5263 | 2000 | 0.2159 | 8.0466 |
| 0.0014 | 13.1579 | 2500 | 0.2185 | 8.1873 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1