metadata
language:
- ru
license: apache-2.0
base_model: openai/whisper-base
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Base Ru - Swedish
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: default
split: test
args: 'config: ru, split: test'
metrics:
- name: Wer
type: wer
value: 27.381068672462632
Whisper Base Ru - Swedish
This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3077
- Wer: 27.3811
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: 16
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.2882 | 0.49 | 1000 | 0.3627 | 30.3885 |
| 0.2675 | 0.98 | 2000 | 0.3264 | 28.4422 |
| 0.1765 | 1.48 | 3000 | 0.3146 | 27.6424 |
| 0.1757 | 1.97 | 4000 | 0.3077 | 27.3811 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 1.13.1
- Datasets 2.15.0
- Tokenizers 0.15.0