metadata
language:
- da
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: Whisper Tiny Da - HollowVoice
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audiofolder
type: audiofolder
config: default
split: train[-20%:]
args: default
metrics:
- name: Wer
type: wer
value: 86.49993452926542
Whisper Tiny Da - HollowVoice
This model is a fine-tuned version of openai/openai/whisper-tiny on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5216
- Wer: 86.4999
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 |
|---|---|---|---|---|
| 0.0319 | 24.39 | 1000 | 0.5216 | 86.4999 |
| 0.0031 | 48.78 | 2000 | 0.5156 | 89.3545 |
| 0.0017 | 73.17 | 3000 | 0.5267 | 89.7342 |
| 0.0013 | 97.56 | 4000 | 0.5312 | 90.9781 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2