---
pipeline_tag: audio-classification
metrics:
- accuracy
---

model_name_or_path = "quaja/hubert-base-amharic-speech-emotion-recognition"
config = AutoConfig.from_pretrained(model_name_or_path)
feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name_or_path)
model = HubertForSpeechClassification.from_pretrained(model_name_or_path).to(device)