Hugging Face's logo

sudoping01
/
maliba-asr-v0

PEFT
Safetensors
Generated from Trainer
Model card Files Community
maliba-asr-v0 / README.md
sudoping01's picture
sudoping01
End of training
0ab7333 verified
preview code
|
raw
history blame contribute delete
1.8 kB
metadata
library_name: peft
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - generated_from_trainer
model-index:
  - name: maliba-asr-v0
    results: []

maliba-asr-v0

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2265

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
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • 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: 6
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4581 0.9998 3502 0.2683
0.3656 1.9998 7004 0.2527
0.3463 2.9998 10506 0.2447
0.2788 3.9998 14008 0.2405
0.2607 4.9998 17510 0.2277
0.202 5.9998 21012 0.2265

Framework versions

  • PEFT 0.14.1.dev0
  • Transformers 4.50.0.dev0
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0