metadata
library_name: transformers
language:
- yo
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- hf-internal-testing/librispeech_asr_dummy
metrics:
- wer
model-index:
- name: Whisper Small yo - fine_tune
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: librispeech_asr_dataset
type: hf-internal-testing/librispeech_asr_dummy
metrics:
- name: Wer
type: wer
value: 6.587473002159827
Whisper Small yo - fine_tune
This model is a fine-tuned version of openai/whisper-small on the librispeech_asr_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1471
- Wer Ortho: 6.6134
- Wer: 6.5875
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: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0123 | 3.2895 | 500 | 0.1471 | 6.6134 | 6.5875 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2