Hugging Face's logo

Apness
/
rururu

Automatic Speech Recognition
Transformers
Safetensors
Russian
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
rururu / README.md
Apness's picture
Apness
Upload 12 files
4a6a9c1 verified
preview code
|
raw
history blame contribute delete
1.65 kB
metadata
language:
  - ru
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: Whisper Small Ru - BMSTU
    results: []

Whisper Small Ru - BMSTU

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: 0.1876
  • Cer: 3.9623

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

Training results

Training Loss Epoch Step Validation Loss Cer
0.1707 0.4924 1000 0.2238 4.8641
0.1641 0.9847 2000 0.1984 4.1821
0.0696 1.4771 3000 0.1921 4.1234
0.0712 1.9695 4000 0.1876 3.9623

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1