metadata
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- team4/8dretnaEN
metrics:
- wer
model-index:
- name: whisperEN
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: 8dretnaEN
type: team4/8dretnaEN
args: 'split: test'
metrics:
- name: Wer
type: wer
value: 29.831932773109244
whisperEN
This model is a fine-tuned version of openai/whisper-small on the 8dretnaEN dataset. It achieves the following results on the evaluation set:
- Loss: 5.8051
- Wer: 29.8319
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: 10
- 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: 5
- training_steps: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.5291 | 0.03 | 5 | 5.8051 | 29.8319 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2