Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results (legacy)
Instructions to use CodingQueen13/distilhubert-finetuned-gtzan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CodingQueen13/distilhubert-finetuned-gtzan with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="CodingQueen13/distilhubert-finetuned-gtzan")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForAudioClassification processor = AutoProcessor.from_pretrained("CodingQueen13/distilhubert-finetuned-gtzan") model = AutoModelForAudioClassification.from_pretrained("CodingQueen13/distilhubert-finetuned-gtzan", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from CodingQueen13/distilhubert-finetuned-gtzan: direct link, hf CLI and curl.
- Browser
- Download file 2.64 kB
-
https://huggingface.co/CodingQueen13/distilhubert-finetuned-gtzan/resolve/main/README.md
- Command line
-
hf download hf://CodingQueen13/distilhubert-finetuned-gtzan/README.md
-
curl -L -o README.md https://huggingface.co/CodingQueen13/distilhubert-finetuned-gtzan/resolve/main/README.md
2.64 kB
| library_name: transformers | |
| license: apache-2.0 | |
| base_model: ntu-spml/distilhubert | |
| tags: | |
| - generated_from_trainer | |
| datasets: | |
| - marsyas/gtzan | |
| metrics: | |
| - accuracy | |
| model-index: | |
| - name: distilhubert-finetuned-gtzan | |
| results: | |
| - task: | |
| name: Audio Classification | |
| type: audio-classification | |
| dataset: | |
| name: GTZAN | |
| type: marsyas/gtzan | |
| config: all | |
| split: train | |
| args: all | |
| metrics: | |
| - name: Accuracy | |
| type: accuracy | |
| value: 0.82 | |
| <!-- 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. --> | |
| # distilhubert-finetuned-gtzan | |
| This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.6191 | |
| - Accuracy: 0.82 | |
| ## 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: cosine | |
| - lr_scheduler_warmup_ratio: 0.1 | |
| - num_epochs: 15 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| | |
| | 2.1554 | 1.0 | 113 | 2.0427 | 0.44 | | |
| | 1.5528 | 2.0 | 226 | 1.5599 | 0.5 | | |
| | 1.3212 | 3.0 | 339 | 1.1755 | 0.6 | | |
| | 0.9075 | 4.0 | 452 | 0.9560 | 0.73 | | |
| | 0.7823 | 5.0 | 565 | 0.8967 | 0.74 | | |
| | 0.7262 | 6.0 | 678 | 0.6578 | 0.8 | | |
| | 0.5761 | 7.0 | 791 | 0.6274 | 0.81 | | |
| | 0.3797 | 8.0 | 904 | 0.6923 | 0.82 | | |
| | 0.4168 | 9.0 | 1017 | 0.5700 | 0.84 | | |
| | 0.2646 | 10.0 | 1130 | 0.6484 | 0.81 | | |
| | 0.1952 | 11.0 | 1243 | 0.5925 | 0.84 | | |
| | 0.1403 | 12.0 | 1356 | 0.6551 | 0.82 | | |
| | 0.1558 | 13.0 | 1469 | 0.6271 | 0.82 | | |
| | 0.4606 | 14.0 | 1582 | 0.6272 | 0.82 | | |
| | 0.2095 | 15.0 | 1695 | 0.6191 | 0.82 | | |
| ### Framework versions | |
| - Transformers 4.44.2 | |
| - Pytorch 2.4.0+cu121 | |
| - Datasets 2.21.0 | |
| - Tokenizers 0.19.1 | |