Downloads · 30 days
2
1% of all-time downloads
wav2vec2-base-960h-finetuned-gtzan2
SiMenz/wav2vec2-base-960h-finetuned-gtzan2
wav2vec2-base-960h-finetuned-gtzan2 is a machine learning model from SiMenz. 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
235
Public
Parameters
94.6M
22.3 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
- Oct 1, 2025
- Updated
- Oct 2, 2025
- SHA
- 37f4a338
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-960h-finetuned-gtzan2
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.9039
- 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2959 | 0.9912 | 56 | 2.2684 | 0.12 |
| 2.2055 | 2.0 | 113 | 2.0581 | 0.26 |
| 2.005 | 2.9912 | 169 | 2.0830 | 0.24 |
| 1.952 | 4.0 | 226 | 1.8202 | 0.35 |
| 1.7 | 4.9912 | 282 | 1.7367 | 0.37 |
| 1.6986 | 6.0 | 339 | 1.5760 | 0.32 |
| 1.5305 | 6.9912 | 395 | 1.5647 | 0.44 |
| 1.4761 | 8.0 | 452 | 1.3515 | 0.56 |
| 1.3411 | 8.9912 | 508 | 1.4492 | 0.49 |
| 1.2898 | 10.0 | 565 | 1.4598 | 0.55 |
| 1.1679 | 10.9912 | 621 | 1.2677 | 0.56 |
| 1.1118 | 12.0 | 678 | 1.1283 | 0.59 |
| 1.0104 | 12.9912 | 734 | 1.2186 | 0.63 |
| 0.9346 | 14.0 | 791 | 1.1662 | 0.59 |
| 0.7825 | 14.9912 | 847 | 0.9510 | 0.73 |
| 0.6248 | 16.0 | 904 | 0.9086 | 0.71 |
| 0.6276 | 16.9912 | 960 | 0.8044 | 0.75 |
| 0.5403 | 18.0 | 1017 | 0.8205 | 0.7 |
| 0.5172 | 18.9912 | 1073 | 0.9126 | 0.77 |
| 0.4416 | 20.0 | 1130 | 0.9827 | 0.78 |
| 0.3819 | 20.9912 | 1186 | 0.9372 | 0.79 |
| 0.3926 | 22.0 | 1243 | 0.9376 | 0.8 |
| 0.3198 | 22.9912 | 1299 | 0.9027 | 0.81 |
| 0.3314 | 24.0 | 1356 | 0.9031 | 0.82 |
| 0.3691 | 24.7788 | 1400 | 0.9039 | 0.82 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.19.1
- Type
- wav2vec2
- Created
- Oct 1, 2025
- Updated
- Oct 2, 2025