marsyas/gtzan
Updated โข 8.35k โข 19
How to use ahk-d/distilhubert-finetuned-gtzan with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("audio-classification", model="ahk-d/distilhubert-finetuned-gtzan") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForAudioClassification
processor = AutoProcessor.from_pretrained("ahk-d/distilhubert-finetuned-gtzan")
model = AutoModelForAudioClassification.from_pretrained("ahk-d/distilhubert-finetuned-gtzan", device_map="auto")This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4594 | 1.0 | 113 | 1.4401 | 0.59 |
| 0.909 | 2.0 | 226 | 1.0519 | 0.68 |
| 0.7199 | 3.0 | 339 | 0.9138 | 0.72 |
| 0.4579 | 4.0 | 452 | 0.7671 | 0.75 |
| 0.4301 | 5.0 | 565 | 0.5310 | 0.84 |
| 0.2227 | 6.0 | 678 | 0.5143 | 0.87 |
| 0.1142 | 7.0 | 791 | 0.5114 | 0.85 |
| 0.04 | 8.0 | 904 | 0.5380 | 0.87 |
| 0.0367 | 9.0 | 1017 | 0.5885 | 0.87 |
| 0.0258 | 10.0 | 1130 | 0.6084 | 0.86 |
Base model
ntu-spml/distilhubert