Downloads · 30 days
6
7% of all-time downloads
distilhubert-finetuned-gtzan
anthony-wss/distilhubert-finetuned-gtzan
distilhubert-finetuned-gtzan is a audio classification model from anthony-wss. 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.
This repo contains code and notes for this tutorial.
All-time downloads
81
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin94.8 MB · 100%
At a glance
- Task
- Audio Classification
- Library
- transformers
- Model type
- hubert
- Access
- Public
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023
- SHA
- a8aa9fc8
Datasets
Model card
From the Hugging Face model README
Audio Classification
This repo contains code and notes for this tutorial.
Dataset
GTZAN is used.
Usage
export HUGGINGFACE_TOKEN=<your_token>
python main.py
Performance
Acc: 0.81 (default setting)
Notes
-
🤗 Datasets support
train_test_split()method to split the dataset. -
feature_extractorcan not handle resampling- To resample, one can use
dataset.map()
- To resample, one can use
from datasets import Audio
gtzan = gtzan.cast_column("audio", Audio(sampling_rate=feature_extractor.sampling_rate))
-
feature_extractordo the normalization and returnsinput_valuesandattention_mask. -
.map()support batched preprocess. -
Why
AutoModelForAudioClassification.from_pretrainedtakeslabel2idandid2label?
- Task
- Audio Classification
- Library
- transformers
- Type
- hubert
- Languages
- en
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023