Hugging Face's logo

ihanif
/
whisper-small-cv20-v2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Pashto
whisper
Generated from Trainer
Model card Files Metrics Community
whisper-small-cv20-v2 / README.md
ihanif's picture
ihanif
End of training
44ffe36 verified
preview code
|
raw
history blame contribute delete
1.55 kB
metadata
library_name: transformers
language:
  - ps
base_model: ihanif/whisper-small-tunning-v2
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
model-index:
  - name: Whisper Small PS - CV20-2
    results: []

Whisper Small PS - CV20-2

This model is a fine-tuned version of ihanif/whisper-small-tunning-v2 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.5003
  • eval_wer_ortho: 50.2740
  • eval_wer: 47.0378
  • eval_runtime: 854.5233
  • eval_samples_per_second: 3.278
  • eval_steps_per_second: 0.051
  • epoch: 0.5128
  • step: 400

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: 5e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0