metadata
library_name: peft
language:
- ne
license: apache-2.0
base_model: kiranpantha/whisper-large-v3-nepali
tags:
- generated_from_trainer
datasets:
- kiranpantha/OpenSLR54-Balanced-Nepali
model-index:
- name: kiranpantha/whisper-large-v3-nepali
results: []
kiranpantha/whisper-large-v3-nepali
This model is a fine-tuned version of kiranpantha/whisper-large-v3-nepali on the OpenSLR54 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3962
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.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: 10
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 14 | 0.6609 |
| 0.7154 | 2.0 | 28 | 0.3891 |
| 0.7154 | 3.0 | 42 | 0.3543 |
| 0.1387 | 4.0 | 56 | 0.3768 |
| 0.1387 | 5.0 | 70 | 0.3557 |
| 0.0933 | 6.0 | 84 | 0.3673 |
| 0.0933 | 7.0 | 98 | 0.3607 |
| 0.0228 | 8.0 | 112 | 0.3853 |
| 0.0105 | 9.0 | 126 | 0.3907 |
| 0.0105 | 10.0 | 140 | 0.3962 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cxx11.abi
- Datasets 3.2.0
- Tokenizers 0.21.0