metadata
language:
- ru
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Ru - v2
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: ru
split: test
args: 'config: ru, split: test'
metrics:
- name: Wer
type: wer
value: 11.208788514118268
Whisper Small Ru - v2
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2108
- Wer Ortho: 15.1680
- Wer: 11.2088
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: 32
- 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 Ortho | Wer |
|---|---|---|---|---|---|
| 0.1678 | 0.9843 | 1000 | 0.2046 | 16.5258 | 12.3257 |
| 0.0885 | 1.9685 | 2000 | 0.1940 | 15.6577 | 11.7703 |
| 0.0407 | 2.9528 | 3000 | 0.1983 | 15.1289 | 11.2725 |
| 0.0186 | 3.9370 | 4000 | 0.2108 | 15.1680 | 11.2088 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1