Hugging Face's logo

kiranpantha
/
whisper-large-v2-nepali-lora-ex-1

PEFT
TensorBoard
Safetensors
Nepali
Generated from Trainer
Model card Files Metrics Community
whisper-large-v2-nepali-lora-ex-1 / README.md
kiranpantha's picture
kiranpantha
End of training
540ee21 verified
preview code
|
raw
history blame contribute delete
1.67 kB
metadata
library_name: peft
language:
  - ne
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
  - generated_from_trainer
datasets:
  - kiranpantha/OpenSLR54-Balanced-Nepali
model-index:
  - name: openai/whisper-large-v2
    results: []

openai/whisper-large-v2

This model is a fine-tuned version of openai/whisper-large-v2 on the OpenSLR54 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2313

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: 50
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.7253 1.0 30 0.3192
0.3053 2.0 60 0.3576
0.2016 3.0 90 0.2313

Framework versions

  • PEFT 0.14.0
  • Transformers 4.47.1
  • Pytorch 2.5.1+cxx11.abi
  • Datasets 3.2.0
  • Tokenizers 0.21.0