metadata
license: apache-2.0
base_model: openai/whisper-base
tags:
- audio-classification
- generated_from_trainer
datasets:
- superb
metrics:
- accuracy
model-index:
- name: superb_si_42
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: superb
type: superb
config: si
split: validation
args: si
metrics:
- name: Accuracy
type: accuracy
value: 0.6013904982618772
superb_si_42
This model is a fine-tuned version of openai/whisper-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 1.7025
- Accuracy: 0.6014
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-05
- train_batch_size: 32
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.4406 | 1.0 | 4324 | 5.5144 | 0.0424 |
| 3.6304 | 2.0 | 8648 | 3.8862 | 0.1867 |
| 2.6868 | 3.0 | 12972 | 2.9909 | 0.3292 |
| 1.9548 | 4.0 | 17296 | 2.6032 | 0.3889 |
| 1.5749 | 5.0 | 21620 | 2.2077 | 0.4778 |
| 1.3105 | 6.0 | 25944 | 2.0726 | 0.5194 |
| 1.1002 | 7.0 | 30268 | 1.9175 | 0.5511 |
| 0.9522 | 8.0 | 34592 | 1.7847 | 0.5899 |
| 0.8263 | 9.0 | 38916 | 1.7225 | 0.5936 |
| 0.7333 | 10.0 | 43240 | 1.7025 | 0.6014 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1