metadata

library_name: transformers
language:
  - hi
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
metrics:
  - wer
model-index:
  - name: Whisper Medium Hi - Amarjeet
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 13.0
          type: mozilla-foundation/common_voice_13_0
          config: hi
          split: None
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 23.48751501097354

Whisper Medium Hi - Amarjeet

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.3223
Wer: 23.4875

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: 16
eval_batch_size: 8
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: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0546	2.3641	1000	0.2291	26.3406
0.0124	4.7281	2000	0.2662	24.4275
0.0007	7.0922	3000	0.3053	23.8147
0.0001	9.4563	4000	0.3223	23.4875

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.21.0