metadata

language:
  - hi
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: Whisper Small En 3
    results: []

Whisper Small En 3

This model is a fine-tuned version of openai/whisper-small on the Common Voice 3.0 dataset. It achieves the following results on the evaluation set:

eval_loss: 0.7635
eval_wer: 126.2971
eval_runtime: 2284.865
eval_samples_per_second: 1.14
eval_steps_per_second: 0.143
epoch: 6.68
step: 5000

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 8000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.39.3
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2