metadata

language:
  - hi
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - konnakol
model-index:
  - name: Whisper Hi - Gopika
    results: []

Whisper Hi - Gopika

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

eval_loss: 0.1745
eval_wer_sentence: 0.0253
eval_cer_sentence: 0.0241
eval_wer_word: 0.0445
eval_cer_word: 0.0223
eval_wer_char: 0.0559
eval_cer_char: 0.0347
eval_runtime: 16.8315
eval_samples_per_second: 2.733
eval_steps_per_second: 0.178
epoch: 8.3333
step: 50

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: 5e-05
train_batch_size: 32
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 1000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1