Downloads · 30 days
5
17% of all-time downloads
whisper-tiny-finetuned-gtzan
paavni/whisper-tiny-finetuned-gtzan
whisper-tiny-finetuned-gtzan is a audio classification model from paavni. Use it for the audio classification task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
29
Public
Parameters
8.3M
399 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors33.2 MB · 100%
At a glance
- Task
- Audio Classification
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Sep 9, 2024
- Updated
- Sep 12, 2024
- SHA
- 2b7ee49f
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
openai/whisper-tiny-finetuned-gtzan
This model is a fine-tuned version of openai/whisper-tiny on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6068
- Accuracy: 0.87
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: 8
- 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_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4287 | 1.0 | 113 | 1.3284 | 0.65 |
| 0.8023 | 2.0 | 226 | 0.9355 | 0.68 |
| 0.5235 | 3.0 | 339 | 0.5613 | 0.81 |
| 0.3177 | 4.0 | 452 | 0.8017 | 0.72 |
| 0.1617 | 5.0 | 565 | 0.6262 | 0.84 |
| 0.0891 | 6.0 | 678 | 0.4760 | 0.9 |
| 0.0071 | 7.0 | 791 | 0.5912 | 0.87 |
| 0.0034 | 8.0 | 904 | 0.5310 | 0.89 |
| 0.0026 | 9.0 | 1017 | 0.5625 | 0.89 |
| 0.0024 | 10.0 | 1130 | 0.6068 | 0.87 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Audio Classification
- Type
- whisper
- License
- apache-2.0
- Created
- Sep 9, 2024
- Updated
- Sep 12, 2024