with-harakah

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.0044
  • eval_wer: 9.4689
  • eval_runtime: 9757.536
  • eval_samples_per_second: 2.05
  • eval_steps_per_second: 0.171
  • epoch: 2.0691
  • step: 137500

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: 8
  • eval_batch_size: 12
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 5

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
809M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for azizillo/with-harakah

Finetuned
(181)
this model