Saltar al contenido
ModelPublicadoExterno
Descargar

Multimodal Emotion Speech Recognition

This model performs emotion recognition from speech using a multimodal approach, utilizing: Audio Model: Wav2Vec2 Base Text/Context Model: RoBERTa Base

Fuentehuggingface.co/dynann/multimodal-emotion-speech-recognition/tree/94ac460089b4def964c89a2589556eb934e96295
TipoOtherModelo baseFacebookAI/roberta-baseVersiónRevision 94ac460

Fuente del modelo

Tipo
Other
Tamaño del archivo
839 MB
Modelo base
FacebookAI/roberta-base
Versión
vRevision 94ac460
Actualizado
19 sept 2026
Descargas
0
Fuente
Hugging Face

Descripción de la fuente

Multimodal Emotion Speech Recognition

Model Description

This model performs emotion recognition from speech using a multimodal approach, utilizing:

  • Audio Model: Wav2Vec2 Base
  • Text/Context Model: RoBERTa Base

Dataset

Evaluation Results

Classification Report

              precision    recall  f1-score   support

         ANG       0.96      0.90      0.93        30
         CAL       0.00      0.00      0.00         0
         DIS       0.86      0.95      0.90        20
         FEA       0.78      0.67      0.72        27
         HAP       0.84      0.79      0.81        33
         NEU       0.89      0.96      0.92        25
         SAD       0.78      0.95      0.86        19
         SUR       0.88      0.78      0.82         9

    accuracy                           0.85       163
   macro avg       0.75      0.75      0.75       163
weighted avg       0.86      0.85      0.85       163

Overall Accuracy: 0.85

Fuentes

1 fuente
Hugging FacePrincipalVersión 94ac460089b4def964c89a2589556eb934e96295
huggingface.co/dynann/multimodal-emotion-speech-recognition/tree/94ac460089b4def964c89a2589556eb934e96295

Verificado 19 sept

Artefactos del modelo

1 artefacto

model.pt

pt · 839 MB · SHA-256 71cbc4ca6119…9680 · Hugging Face

Descargar

Extractos de fuentes

2 extractos
Readme19 septhuggingface.co/dynann/multimodal-emotion-speech-recognition

--- license: apache-2.0 datasets: - stapesai/ssi-speech-emotion-recognition metrics: - accuracy - precision - recall - f1 pipeline_tag: audio-classification base_model: - facebook/wav2vec2-base - FacebookAI/roberta-base tags: - asr --- # Multimodal Emotion Speech Recognition ## Model Description This model performs emotion recognition from speech using a multimodal approach, utilizing: - **Audio Model**: Wav2Vec2 Base - **Text/Context Model**: RoBERTa Base ## Dataset - **Dataset Name**: [stapesai/ssi-speech-emotion-recognition](https://huggingface.co/datasets/stapesai/ssi-speech-emotion-recognition) ## Evaluation Results ### Classification Report ``` precision recall f1-score support ANG 0.96 0.90 0.93 30 CAL 0.00 0.00 0.00 0 DIS 0.86 0.95 0.90 20 FEA 0.78 0.67 0.72 27 HAP 0.84 0.79 0.81 33 NEU 0.89 0.96 0.92 25 SAD 0.78 0.95 0.86 19 SUR 0.88 0.78 0.82 9 accuracy 0.85 163 macro avg 0.75 0.75 0.75 163 weighted avg 0.86 0.85 0.85 163 ``` **Overall Accuracy**: 0.85

Note19 septhuggingface.co/dynann/multimodal-emotion-speech-recognition

Source context: 0 downloads · 0 likes · Pipeline audio-classification · Repo dynann/multimodal-emotion-speech-recognition