Downloads · 30 days
11
2% of all-time downloads
ast-fleurs-langid-dropout-0.2
sanchit-gandhi/ast-fleurs-langid-dropout-0.2
ast-fleurs-langid-dropout-0.2 is a audio classification model from sanchit-gandhi. Use it for the audio classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as bsd-3-clause.
should probably proofread and complete it, then remove this comment. --
All-time downloads
500
Public
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin345 MB · 100%
At a glance
- Task
- Audio Classification
- Library
- transformers
- License
- bsd-3-clause
- Model type
- audio-spectrogram-transformer
- Access
- Public
- Created
- Feb 6, 2023
- Updated
- Feb 8, 2023
- SHA
- daa66668
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. -->
ast-fleurs-langid-dropout-0.2
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 7.3600
- Accuracy: 0.1819
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: 4
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0251 | 1.0 | 16987 | 6.7973 | 0.1689 |
| 0.0007 | 2.0 | 33974 | 7.3461 | 0.1787 |
| 0.0 | 3.0 | 50961 | 7.3600 | 0.1819 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Audio Classification
- Library
- transformers
- Type
- audio-spectrogram-transformer
- License
- bsd-3-clause
- Created
- Feb 6, 2023
- Updated
- Feb 8, 2023