# Load model directly
from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
extractor = AutoFeatureExtractor.from_pretrained("abletobetable/spec_soul_ast_aug")
model = AutoModelForAudioClassification.from_pretrained("abletobetable/spec_soul_ast_aug", device_map="auto")Quick Links
Finetuned Audio Spectrogram Transformer for sentiment analysis in russian with audio augmentation
github repo with code and tg bot
init state: MIT/ast-finetuned-audioset-10-10-0.4593
- Downloads last month
- 7
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="abletobetable/spec_soul_ast_aug")