README.md

metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny.en
tags:
  - product-search
  - e-commerce
  - voice-search
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Tiny Product Search - Your Name
    results: []

Whisper Tiny Product Search - Your Name

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

• Loss: 2.6980
• Wer: 69.2308

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use 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: 2
• training_steps: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.5491	1.6667	5	3.9844	61.5385
2.95	3.3333	10	2.6980	69.2308

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3