Downloads · 30 days
9
17% of all-time downloads
wav2vec2-base-100k-finetuned-gtzan
Jekaterina/wav2vec2-base-100k-finetuned-gtzan
wav2vec2-base-100k-finetuned-gtzan is a machine learning model from Jekaterina. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
52
Public
Parameters
94.6M
1.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Model type
- wav2vec2
- Access
- Public
- Created
- Sep 11, 2024
- Updated
- Sep 11, 2024
- SHA
- a936f7b5
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. -->
wav2vec2-base-100k-finetuned-gtzan
This model is a fine-tuned version of m3hrdadfi/wav2vec2-base-100k-gtzan-music-genres on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.8208
- Accuracy: 0.96
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9319 | 1.0 | 113 | 1.8502 | 0.78 |
| 1.5211 | 2.0 | 226 | 1.4238 | 0.86 |
| 1.1818 | 3.0 | 339 | 1.1062 | 0.92 |
| 0.8895 | 4.0 | 452 | 0.8764 | 0.95 |
| 0.8228 | 5.0 | 565 | 0.8208 | 0.96 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Type
- wav2vec2
- Created
- Sep 11, 2024
- Updated
- Sep 11, 2024