Downloads · 30 days
6
7% of all-time downloads
ser-fast-cnn-bilstm
MathRaaj/ser-fast-cnn-bilstm
ser-fast-cnn-bilstm is a machine learning model from MathRaaj. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model was trained from scratch on the RAVDESS and TESS datasets.
All-time downloads
81
Public
Repo size
31.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin31.5 MB · 100%
At a glance
- Model type
- cnn-bilstm-attention
- Access
- Public
- Created
- Apr 7, 2026
- Updated
- Apr 7, 2026
- SHA
- 5eb5832f
Model card
From the Hugging Face model README
Speech Emotion Recognition (CNN-BiLSTM-Attention)
This model was trained from scratch on the RAVDESS and TESS datasets.
Model Architecture
- Front-end: 4-block CNN for feature extraction from Mel Spectrograms.
- Mid-section: Bidirectional LSTM for temporal dependencies.
- Pooling: Multi-head Attention pooling.
- Back-end: Fully connected classifier.
Classes
0: neutral, 1: calm, 2: happy, 3: sad, 4: angry, 5: fearful, 6: disgust
- Type
- cnn-bilstm-attention
- Languages
- en
- Created
- Apr 7, 2026
- Updated
- Apr 7, 2026