metadata
language:
- id
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Medium Id - Rio Gunawan
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: mozilla-foundation/common_voice_17_0
config: id
split: None
args: 'config: id, split: test'
metrics:
- name: Wer
type: wer
value: 12.877627732145344
Whisper Medium Id - Rio Gunawan
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2638
- Wer: 12.8776
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 |
---|---|---|---|---|
0.1352 | 1.9231 | 1000 | 0.1943 | 13.3695 |
0.0167 | 3.8462 | 2000 | 0.2161 | 12.6131 |
0.0024 | 5.7692 | 3000 | 0.2483 | 12.5064 |
0.0008 | 7.6923 | 4000 | 0.2638 | 12.8776 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1