metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- vahn98/bb-audio-wp
metrics:
- wer
model-index:
- name: Whisper-bb
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audio-bb
type: vahn98/bb-audio-wp
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 79.59183673469387
Whisper-bb
This model is a fine-tuned version of openai/whisper-small on the audio-bb dataset. It achieves the following results on the evaluation set:
- Loss: 1.3749
- Wer: 79.5918
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 |
|---|---|---|---|---|
| 0.0 | 1000.0 | 1000 | 1.3448 | 51.0204 |
| 0.0 | 2000.0 | 2000 | 1.3630 | 79.5918 |
| 0.0 | 3000.0 | 3000 | 1.3730 | 79.5918 |
| 0.0 | 4000.0 | 4000 | 1.3749 | 79.5918 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1