metadata
language:
- en
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- physician_dictation_gpt_4_turbo
metrics:
- wer
model-index:
- name: Whisper Large v3 Physician Dictation GPT 4 turbo
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Physician Dictation GPT 4 Turbo
type: physician_dictation_gpt_4_turbo
config: default
split: None
args: 'config: en, split: test'
metrics:
- name: Wer
type: wer
value: 4.8915240533620805
Whisper Large v3 Physician Dictation GPT 4 turbo
This model is a fine-tuned version of openai/whisper-medium on the Physician Dictation GPT 4 Turbo dataset. It achieves the following results on the evaluation set:
- Loss: 0.1358
- Wer: 4.8915
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: 4
- 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 |
---|---|---|---|---|
0.0039 | 7.9365 | 1000 | 0.1131 | 5.1925 |
0.001 | 15.8730 | 2000 | 0.1258 | 5.0712 |
0.0001 | 23.8095 | 3000 | 0.1329 | 4.9364 |
0.0001 | 31.7460 | 4000 | 0.1358 | 4.8915 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1