Audio Classification
Transformers
Safetensors
smad_crnn
feature-extraction
audio
music
speech
custom-code
custom_code
Instructions to use duclvQ/smad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use duclvQ/smad with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="duclvQ/smad", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("duclvQ/smad", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SmadForAudioClassification" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_smad.SmadConfig", | |
| "AutoModel": "modeling_smad.SmadForAudioClassification", | |
| "AutoModelForAudioClassification": "modeling_smad.SmadForAudioClassification" | |
| }, | |
| "channels": [ | |
| 32, | |
| 64, | |
| 128, | |
| 128 | |
| ], | |
| "dropout": 0.2, | |
| "id2label": { | |
| "0": "speech_noise", | |
| "1": "speech_music", | |
| "2": "singing_music", | |
| "3": "none" | |
| }, | |
| "label2id": { | |
| "speech_noise": 0, | |
| "speech_music": 1, | |
| "singing_music": 2, | |
| "none": 3 | |
| }, | |
| "model_type": "smad_crnn", | |
| "n_fft": 400, | |
| "num_labels": 4, | |
| "num_mels": 80, | |
| "rnn_hidden": 128, | |
| "rnn_type": "gru", | |
| "sample_rate": 16000, | |
| "segment_seconds": 4.0, | |
| "temperature": 0.709507268312107 | |
| } | |