Hugging Face's logo

Mark-X
/
whisper-small-or

TensorBoard
Safetensors
Oriya
whisper
Generated from Trainer
Eval Results
Model card Files Metrics Community
whisper-small-or / README.md
Mark-X's picture
Mark-X
End of training
128cb71 verified
preview code
|
raw
history blame
1.44 kB
metadata
library_name: transformers
language:
  - or
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
model-index:
  - name: whisper-small-or
    results: []

whisper-small-or

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

  • eval_loss: 0.2320
  • eval_wer: 54.4920
  • eval_runtime: 631.1053
  • eval_samples_per_second: 1.103
  • eval_steps_per_second: 0.138
  • epoch: 7.8125
  • step: 1000

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: 5000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1