metadata

language:
  - ru
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - tbkazakova/even_speech_biblical
metrics:
  - wer
model-index:
  - name: Whisper Small Even - VovaK13
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Even Speech Biblical
          type: tbkazakova/even_speech_biblical
          config: default
          split: None
          args: 'config: ru, split: train'
        metrics:
          - name: Wer
            type: wer
            value: 30.275689223057643

Whisper Small Even - VovaK13

This model is a fine-tuned version of openai/whisper-small on the Even Speech Biblical dataset. It achieves the following results on the evaluation set:

Loss: 0.4483
Wer: 30.2757

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: 250
training_steps: 2500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0509	5.9880	500	0.3699	33.7343
0.0022	11.9760	1000	0.4084	30.9273
0.0003	17.9641	1500	0.4336	30.1253
0.0002	23.9521	2000	0.4444	30.2757
0.0002	29.9401	2500	0.4483	30.2757

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1