metadata
base_model: openai/whisper-large-v3
library_name: transformers
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: whisper-large-v3-natbed-native-model
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: natbed
type: natbed
config: en
split: test
metrics:
- type: wer
value: 43.06
name: WER
whisper-large-v3-natbed-native-model
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8157
- Wer: 53.5669
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: 1.75e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 30000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.4403 | 0.7013 | 250 | 0.8207 | 61.9634 |
| 0.7263 | 1.4025 | 500 | 0.7642 | 56.5183 |
| 0.6316 | 2.1038 | 750 | 0.7486 | 54.5928 |
| 0.4615 | 2.8050 | 1000 | 0.7218 | 51.1206 |
| 0.3381 | 3.5063 | 1250 | 0.7561 | 52.2569 |
| 0.2662 | 4.2076 | 1500 | 0.8242 | 52.5095 |
| 0.1788 | 4.9088 | 1750 | 0.8157 | 53.5669 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1