wav2vec2_speech_emotion_recognition_trained_on_IEMOCAP_onnx
/
wav2vec2_speech_emotion_recognition_trained_on_IEMOCAP.yaml
| feature_extractor: Wav2Vec2FeatureExtractor | |
| full_name: canlinzhang/wav2vec2_speech_emotion_recognition_trained_on_IEMOCAP | |
| labels: | |
| 0: neu | |
| 1: ang | |
| 2: sad | |
| 3: hap | |
| model: Wav2Vec2ForSequenceClassification | |
| sampling_rate: 16000 | |
| shape: | |
| - 1 | |
| - 320000 | |