Skip to content
ModelVerifiedExternal
Download

Whisper Medium Libyan

This model is a fine-tuned version of openai/whisper-medium on the Custom Libyan Arabic podcast — 258 manually transcribed clips dataset. It achieves the following results on the evaluation set: Loss: 0.7577 Wer: 34.7790

KindText modelBase modelopenai/whisper-mediumVersionFP32Publisher@RhaodghCgrade

Model source

Kind
Text model
File size
2.85 GB
Base model
openai/whisper-medium
Version
vFP32
Updated
Nov 2, 2026
Publisher
@Rhaodgh
Downloads
8
Source
Hugging Face

Source description

Whisper medium — Libyan Arabic Dialect

This model is a fine-tuned version of openai/whisper-medium on the Custom Libyan Arabic podcast — 258 manually transcribed clips dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7577
  • Wer: 34.7790

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 25
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.15666.68971000.564734.1952
0.024213.34482000.633335.2794
0.012020.03000.712635.7798
0.001826.68974000.748035.0292
0.001433.34485000.757734.7790

Framework versions

  • Transformers 5.12.0
  • Pytorch 2.11.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrimaryVersion bad248634a4381bdfd3a2db49ad081006ba58d81
huggingface.co/Rhaodgh/whisper-medium-libyan/tree/bad248634a4381bdfd3a2db49ad081006ba58d81

Verified Nov 2

Download files

Model artifacts

1 artifact

model.safetensors

safetensors · FP32 (unverified) · 2.85 GB · SHA-256 a21e02c87153…6091 · Hugging Face

Download file

Source excerpts

3 excerpts

--- library_name: transformers language: - ar license: apache-2.0 base_model: openai/whisper-medium tags: - generated_from_trainer metrics: - wer model-index: - name: "Whisper medium \u2014 Libyan Arabic Dialect" results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper medium — Libyan Arabic Dialect This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Custom Libyan Arabic podcast — 258 manually transcribed clips dataset. It achieves the following results on the evaluation set: - Loss: 0.7577 - Wer: 34.7790 ## 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: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 25 - training_steps: 500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-------:|:----:|:---------------:|:-------:| | 0.1566 | 6.6897 | 100 | 0.5647 | 34.1952 | | 0.0242 | 13.3448 | 200 | 0.6333 | 35.2794 | | 0.0120 | 20.0 | 300 | 0.7126 | 35.7798 | | 0.0018 | 26.6897 | 400 | 0.7480 | 35.0292 | | 0.0014 | 33.3448 | 500 | 0.7577 | 34.7790 | ### Framework versions - Transformers 5.12.0 - Pytorch 2.11.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2

Source context: 8 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo Rhaodgh/whisper-medium-libyan

Source context: 5 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo Rhaodgh/whisper-medium-libyan