metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- whisper-event
- generated_from_trainer
datasets:
- common_voice_15_0
metrics:
- wer
model-index:
- name: Whisper da-nst
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_15_0
type: common_voice_15_0
config: da
split: test
args: da
metrics:
- name: Wer
type: wer
value: 28.276087362329662
Whisper da-nst
This model is a fine-tuned version of openai/whisper-medium on the common_voice_15_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7829
- Wer: 28.2761
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: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.0046 | 4.03 | 1000 | 0.7389 | 31.9209 |
| 0.003 | 9.02 | 2000 | 0.7225 | 29.6108 |
| 0.0001 | 14.01 | 3000 | 0.7554 | 28.3788 |
| 0.0 | 18.04 | 4000 | 0.7761 | 28.3508 |
| 0.0 | 23.03 | 5000 | 0.7829 | 28.2761 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1