Hugging Face's logo

girikabin
/
whisper-NEPALI-LARGE-v2-common-17

PEFT
TensorBoard
Safetensors
Nepali (macrolanguage)
Generated from Trainer
Model card Files Metrics Community
whisper-NEPALI-LARGE-v2-common-17 / README.md
girikabin's picture
girikabin
End of training
7d1b1ed verified
preview code
|
raw
history blame contribute delete
1.73 kB
metadata
library_name: peft
language:
  - nep
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
model-index:
  - name: Whisper Large v2 Hi - Kabin
    results: []

Whisper Large v2 Hi - Kabin

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3904

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 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
1.553 0.6944 25 0.8388
0.508 1.3889 50 0.4456
0.3276 2.0833 75 0.3984
0.16 2.7778 100 0.3904

Framework versions

  • PEFT 0.9.0
  • Transformers 4.46.0.dev0
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.1