metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: whisper-tiny-ak
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audiofolder
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Wer
type: wer
value: 61.9195
whisper-tiny-ak
This model is a fine-tuned version of openai/whisper-tiny on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8641
- Wer: 61.9195
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 |
|---|---|---|---|---|
| 0.1919 | 13.3333 | 1000 | 0.8641 | 61.9195 |
| 0.0111 | 26.6667 | 2000 | 1.1524 | 64.9256 |
| 0.0031 | 40.0 | 3000 | 1.2699 | 63.7272 |
| 0.0022 | 53.3333 | 4000 | 1.3054 | 66.8831 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1