Hugging Face's logo

ihanif
/
whisper-base-synth-v1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Pashto
whisper
Generated from Trainer
Model card Files Metrics Community
whisper-base-synth-v1 / README.md
ihanif's picture
ihanif
End of training
c5b7e0e verified
preview code
|
raw
history blame contribute delete
1.55 kB
metadata
library_name: transformers
language:
  - ps
base_model: ihanif/whisper-base-cv20-v2
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
model-index:
  - name: whisper-base-synth-v1
    results: []

whisper-base-synth-v1

This model is a fine-tuned version of ihanif/whisper-base-cv20-v2 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • eval_loss: 1.4352
  • eval_wer_ortho: 816.3428
  • eval_wer: 837.2591
  • eval_runtime: 1020.837
  • eval_samples_per_second: 2.744
  • eval_steps_per_second: 0.043
  • epoch: 3.1915
  • step: 300

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 OptimizerNames.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: 100
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.6.0+cu124
  • Datasets 3.5.0
  • Tokenizers 0.21.1