feature_extractor: Wav2Vec2FeatureExtractor | |
full_name: DunnBC22/wav2vec2-base-Speech_Emotion_Recognition | |
labels: | |
0: SAD | |
1: ANGRY | |
2: DISGUST | |
3: FEAR | |
4: HAPPY | |
5: NEUTRAL | |
model: Wav2Vec2ForSequenceClassification | |
sampling_rate: 16000 | |
shape: | |
- 1 | |
- 320000 | |