metadata

library_name: transformers
language:
  - ur
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_0
model-index:
  - name: Whisper Small ur - Urdu
    results: []
metrics:
  - cer
pipeline_tag: automatic-speech-recognition

Whisper Small ur - Urdu

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.9090
Cer: 31.9947

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
gradient_accumulation_steps: 4
total_train_batch_size: 64
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: 50
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0017	31.256	1000	0.9090	31.9947

Framework versions

Transformers 4.47.1
Pytorch 2.5.0
Datasets 3.2.0
Tokenizers 0.21.0