metadata
library_name: peft
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- base_model:adapter:openai/whisper-large-v3
- lora
- transformers
model-index:
- name: largeV3-model
results: []
largeV3-model
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.9277
- eval_wer: 0.5778
- eval_cer: 0.1896
- eval_runtime: 1168.519
- eval_samples_per_second: 0.532
- eval_steps_per_second: 0.067
- epoch: 3.9411
- step: 8000
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: 5e-06
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- 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: cosine
- lr_scheduler_warmup_steps: 500
- training_steps: 10000
- mixed_precision_training: Native AMP
Framework versions
- PEFT 0.18.0
- Transformers 5.0.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.22.1