metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- nyagen
metrics:
- wer
model-index:
- name: whisper-large-v3-nyagen-balanced-model
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: nyagen
type: nyagen
metrics:
- name: Wer
type: wer
value: 0.24026512013256007
whisper-large-v3-nyagen-balanced-model
This model is a fine-tuned version of openai/whisper-large-v3 on the nyagen dataset. It achieves the following results on the evaluation set:
- Loss: 0.3155
- Wer: 0.2403
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|
| 1.426 | 1.0756 | 200 | 0.4108 | 0.3070 |
| 0.6798 | 2.1511 | 400 | 0.3343 | 0.2867 |
| 0.3574 | 3.2267 | 600 | 0.3155 | 0.2403 |
| 0.2691 | 4.3023 | 800 | 0.3365 | 0.2158 |
| 0.1851 | 5.3779 | 1000 | 0.3159 | 0.2904 |
| 0.0715 | 6.4534 | 1200 | 0.3676 | 0.2084 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0