Whisper Uz

🚀 Whisper Medium Uzbek

This model is a fine - tuned version of [openai/whisper - medium](https://huggingface.co/openai/whisper - medium) on the Common Voice 17.0 dataset, which can be used for automatic speech recognition tasks.

🚀 Quick Start

This model is a fine - tuned version of [openai/whisper - medium](https://huggingface.co/openai/whisper - medium) on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4148
• Wer: 38.1999

📚 Documentation

Model Information

Model Index

• Name: Whisper Medium Uzbek
  • Results:
    • Task:
      • Name: Automatic Speech Recognition
      • Type: automatic - speech - recognition
    • Dataset:
      • Name: Common Voice 17.0
      • Type: mozilla - foundation/common_voice_17_0
      • Config: uz
      • Split: None
      • Args: 'config: uz, split: test'
    • Metrics:
      • Name: Wer
      • Type: wer
      • Value: 38.19985168705969

Training Procedure

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e - 05
• train_batch_size: 64
• eval_batch_size: 16
• 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_steps: 200
• training_steps: 1500

Training Results

Framework Versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0

📄 License

This project is licensed under the apache - 2.0 license.