metadata
library_name: transformers
language:
- dk
license: apache-2.0
base_model: openai/whisper-large
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- alexandrainst/ftspeech
metrics:
- wer
model-index:
- name: Whisper Large FTSpeech - Your Name
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: ftspeech
type: alexandrainst/ftspeech
args: 'split: test'
metrics:
- name: Wer
type: wer
value: 24.476331512025737
Whisper Large FTSpeech - Your Name
This model is a fine-tuned version of openai/whisper-large on the ftspeech dataset. It achieves the following results on the evaluation set:
- Loss: 0.3820
- Wer: 24.4763
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: Use OptimizerNames.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: 200
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5793 | 0.0032 | 200 | 0.5536 | 30.4519 |
| 0.4187 | 0.0064 | 400 | 0.4508 | 27.5208 |
| 0.3587 | 0.0096 | 600 | 0.4125 | 25.5569 |
| 0.3477 | 0.0129 | 800 | 0.3907 | 24.9318 |
| 0.3786 | 0.0161 | 1000 | 0.3820 | 24.4763 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.21.0