Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v3
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:
- eval_loss: 3.8257
- eval_runtime: 1.4346
- eval_samples_per_second: 0.697
- eval_steps_per_second: 0.697
- epoch: 2.0
- step: 142
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: 10
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 50
- mixed_precision_training: Native AMP
Framework versions
- PEFT 0.9.1.dev0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for Awaz-e-Sehat/whisper-large-v3
Base model
openai/whisper-large-v3