metadata
language:
- en
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- Kiniu/go_dataset
metrics:
- wer
model-index:
- name: whisper_go
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: go_dataset
type: Kiniu/go_dataset
config: go_dataset
split: train
args: 'split: test'
metrics:
- name: Wer
type: wer
value: 190.5437352245863
whisper_go
This model is a fine-tuned version of openai/whisper-small on the go_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.3608
- Wer: 190.5437
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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0369 | 4.71 | 1000 | 0.2629 | 76.9137 |
| 0.0015 | 9.41 | 2000 | 0.3291 | 110.8992 |
| 0.0018 | 14.12 | 3000 | 0.3530 | 181.1038 |
| 0.0006 | 18.82 | 4000 | 0.3608 | 190.5437 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2