metadata
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- generated_from_trainer
datasets:
- ambient_noise_audio
model-index:
- name: whisper_large_v3_turbo_noise_redux_v6
results: []
whisper_large_v3_turbo_noise_redux_v6
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the ambient_noise_audio dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1497
- eval_runtime: 392.7243
- eval_samples_per_second: 1.467
- eval_steps_per_second: 1.467
- epoch: 2.0
- step: 48
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: 0.0002
- train_batch_size: 6
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Framework versions
- Transformers 4.39.3
- Pytorch 2.4.1+cu124
- Datasets 2.18.0
- Tokenizers 0.15.2