metadata
language:
- fi
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper medium Finnish CV 4K
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0 fi
type: mozilla-foundation/common_voice_11_0
config: fi
split: test
args: fi
metrics:
- name: Wer
type: wer
value: 15.736901620806634
Whisper medium Finnish CV 4K
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 fi dataset. It achieves the following results on the evaluation set:
- Loss: 0.3412
- Wer: 15.7369
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: 64
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.0014 | 19.0 | 1000 | 0.3029 | 16.3117 |
| 0.0002 | 38.01 | 2000 | 0.3412 | 15.7369 |
| 0.0001 | 57.01 | 3000 | 0.3592 | 15.8783 |
| 0.0001 | 76.01 | 4000 | 0.3655 | 15.8594 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2