metadata
library_name: transformers
language:
- ur
license: apache-2.0
base_model: GogetaBlueMUI/whisper-medium-ur-jalandhary
tags:
- generated_from_trainer
datasets:
- mirfan899/jalandhary_asr
metrics:
- wer
model-index:
- name: Whisper Medium Ur - Jalandhary ASR Fine-Tuned
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Jalandhary ASR
type: mirfan899/jalandhary_asr
args: 'split: test'
metrics:
- name: Wer
type: wer
value: 18.709390064975896
Whisper Medium Ur - Jalandhary ASR Fine-Tuned
This model is a fine-tuned version of GogetaBlueMUI/whisper-medium-ur-jalandhary on the Jalandhary ASR dataset. It achieves the following results on the evaluation set:
- Loss: 0.1395
- Wer: 18.7094
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-06
- train_batch_size: 8
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1443 | 0.4859 | 500 | 0.1518 | 19.8360 |
| 0.1315 | 0.9718 | 1000 | 0.1395 | 18.7094 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.2
- Tokenizers 0.21.0