metadata
library_name: transformers
language:
- pa
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
datasets:
- cdactvm/punjabi_v1
metrics:
- wer
model-index:
- name: Punjabi Whisper Base - Keval Sakhiya
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: cdactvm/punjabi_v1
args: 'config: pa, split: test'
metrics:
- name: Wer
type: wer
value: 66.0377358490566
Punjabi Whisper Base - Keval Sakhiya
This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7616
- Wer: 66.0377
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: 0.0001
- 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: 50
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1553 | 7.1429 | 50 | 1.1833 | 124.2925 |
| 0.0659 | 14.2857 | 100 | 0.6407 | 73.5849 |
| 0.0065 | 21.4286 | 150 | 0.7339 | 71.6981 |
| 0.0005 | 28.5714 | 200 | 0.7616 | 66.0377 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0