metadata
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- honzapucalek/impaired_v3_independent_moderate
metrics:
- wer
model-index:
- name: impaired-v3-independent-moderate
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: honzapucalek/impaired_v3_independent_moderate cs
type: honzapucalek/impaired_v3_independent_moderate
config: cs
split: test
args: cs
metrics:
- name: Wer
type: wer
value: 0.19775357385976855
impaired-v3-independent-moderate
This model is a fine-tuned version of openai/whisper-large-v3 on the honzapucalek/impaired_v3_independent_moderate cs dataset. It achieves the following results on the evaluation set:
- Loss: 0.6960
- Wer: 0.1978
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0012 | 22.47 | 1000 | 0.5175 | 0.1984 |
| 0.0001 | 44.94 | 2000 | 0.6260 | 0.1995 |
| 0.0 | 67.42 | 3000 | 0.6666 | 0.1986 |
| 0.0 | 89.89 | 4000 | 0.6882 | 0.1978 |
| 0.0 | 112.36 | 5000 | 0.6960 | 0.1978 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1