Hugging Face's logo

kozak-vaclav
/
whisper-tiny-cs

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Czech
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-tiny-cs / README.md
kozak-vaclav's picture
kozak-vaclav
End of training
ed400f6 verified
preview code
|
raw
history blame
1.44 kB
metadata
language:
  - cs
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
model-index:
  - name: Whisper Tiny Czech - Kobrasoft
    results: []

Whisper Tiny Czech - Kobrasoft

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.4534
  • eval_wer: 40.8165
  • eval_runtime: 2156.5456
  • eval_samples_per_second: 4.204
  • eval_steps_per_second: 0.526
  • epoch: 3.2913
  • step: 6000

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: 20000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1