whisper-large-v3-turbo-sq

This model is a fine-tuned version of openai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0986
• Wer: 10.2978

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: 48
• eval_batch_size: 32
• seed: 42
• 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: 500
• training_steps: 50892
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 5.12.0
• Pytorch 2.11.0+cu128
• Datasets 5.0.0
• Tokenizers 0.22.2

Development and attribution

• Original Whisper architecture and base weights: OpenAI, through openai/whisper-large-v3-turbo
• Albanian ASR adaptation, training-data curation, checkpoint preparation, evaluation, packaging, and release: Kushtrim Visoka
• Model card and ongoing maintenance: Kushtrim Visoka

Acknowledgements

This work builds on openai/whisper-large-v3-turbo and the work of its original authors. The upstream architecture and base weights remain the work of their respective creators. This repository documents the task-specific adaptation and release work carried out by Kushtrim Visoka and does not claim authorship of the original model. Dataset creators and tool authors referenced elsewhere in this card should also be cited according to their licenses and documentation.

Citation

If you use this fine-tuned model, please cite this repository and the original upstream model.

@misc{visoka_whisper_large_v3_turbo_albanian_3000_2026,
  author       = {Visoka, Kushtrim},
  title        = {Whisper Large V3 Turbo Albanian, Step 3000},
  year         = {2026},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/Kushtrim/whisper-large-v3-turbo-sq-3000},
  note         = {Fine-tuned derivative of openai/whisper-large-v3-turbo}
}