metadata
language:
- az
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Large v3 Ai - Nurlan Salahaddinov
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: mozilla-foundation/common_voice_17_0
config: az
split: None
args: 'config: az, split: test'
metrics:
- name: Wer
type: wer
value: 28.68525896414343
Whisper Large v3 Ai - Nurlan Salahaddinov
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5938
- Wer: 28.6853
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0 | 142.8571 | 1000 | 0.4999 | 27.4900 |
| 0.0 | 285.7143 | 2000 | 0.5441 | 28.2869 |
| 0.0 | 428.5714 | 3000 | 0.5710 | 28.2869 |
| 0.0 | 571.4286 | 4000 | 0.5869 | 28.6853 |
| 0.0 | 714.2857 | 5000 | 0.5938 | 28.6853 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1