Audio Classification
MLX
audio
speech-emotion-recognition
emotion-recognition
emotion2vec
data2vec
apple-silicon
Instructions to use mlx-community/emotion2vec-plus-large-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/emotion2vec-plus-large-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir emotion2vec-plus-large-mlx mlx-community/emotion2vec-plus-large-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "model_type": "emotion2vec_plus_large", | |
| "architecture": "data2vec2", | |
| "num_classes": 9, | |
| "hidden_dim": 1024, | |
| "ffn_dim": 4096, | |
| "num_layers": 12, | |
| "num_context_blocks": 4, | |
| "num_shared_blocks": 8, | |
| "num_heads": 16, | |
| "conv_feature_layers": [ | |
| [ | |
| 1, | |
| 512, | |
| 10, | |
| 5 | |
| ], | |
| [ | |
| 512, | |
| 512, | |
| 3, | |
| 2 | |
| ], | |
| [ | |
| 512, | |
| 512, | |
| 3, | |
| 2 | |
| ], | |
| [ | |
| 512, | |
| 512, | |
| 3, | |
| 2 | |
| ], | |
| [ | |
| 512, | |
| 512, | |
| 3, | |
| 2 | |
| ], | |
| [ | |
| 512, | |
| 512, | |
| 2, | |
| 2 | |
| ], | |
| [ | |
| 512, | |
| 512, | |
| 2, | |
| 2 | |
| ] | |
| ], | |
| "pos_conv_depth": 5, | |
| "pos_conv_kernel": 19, | |
| "pos_conv_groups": 16, | |
| "feature_dim": 512, | |
| "has_context_norm": true, | |
| "has_extra_tokens": true, | |
| "has_alibi_scale": true, | |
| "num_extra_tokens": 10, | |
| "layer_norm_first": false, | |
| "dtype": "float16", | |
| "emotion_labels": [ | |
| "angry", | |
| "disgusted", | |
| "fearful", | |
| "happy", | |
| "neutral", | |
| "other", | |
| "sad", | |
| "surprised", | |
| "unknown" | |
| ] | |
| } |