Hugging Face's logo

hackergeek98
/
whisper-fa-tinyyy

Automatic Speech Recognition
Transformers
Safetensors
Persian
whisper
Generated from Trainer
Model card Files Community
whisper-fa-tinyyy / README.md
hackergeek98's picture
hackergeek98
Upload 11 files
ac52ee7 verified
preview code
|
raw
history blame
1.55 kB
metadata
library_name: transformers
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
model-index:
  - name: whisper-fa-tinyyy
    results: []

whisper-fa-tinyyy

This model is a fine-tuned version of openai/whisper-tiny on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0246

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • 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_steps: 500
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.0186 0.9998 2357 0.0246

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.6.0+cu124
  • Datasets 3.4.1
  • Tokenizers 0.21.1