README.md

metadata

language:
  - ur
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_14_0
metrics:
  - wer
model-index:
  - name: Whisper Large Ur
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 14.0
          type: mozilla-foundation/common_voice_14_0
          config: ur
          split: test
          args: ur
        metrics:
          - name: Wer
            type: wer
            value: 34.28703990102072

Whisper Large Ur

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 14.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5744
• Wer: 34.2870

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: 32
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0134	9.07	1000	0.5744	34.2870

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.2.dev0
• Tokenizers 0.15.0