Instructions to use Rajaram1996/Hubert_emotion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rajaram1996/Hubert_emotion with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="Rajaram1996/Hubert_emotion")# Load model directly from transformers import AutoProcessor, HubertForSpeechClassification processor = AutoProcessor.from_pretrained("Rajaram1996/Hubert_emotion") model = HubertForSpeechClassification.from_pretrained("Rajaram1996/Hubert_emotion", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Datasets used to train the model
#3
by pembatt - opened
Hello,
Could you provide information on what datasets were used to train the model
I have similar question. May I also know what language this model target for?
I tried to test it on my test dataset while the accuracy is only 22% on 7 class emotion.
{'accuracy': 0.22372881355932203,
'Weighted F1': 0.2164919626503917,
'Micro F1': 0.22372881355932203,
'Macro F1': 0.19736953281826414,
'Weighted Recall': 0.22372881355932203,
'Micro Recall': 0.22372881355932203,
'Macro Recall': 0.20406851265096204,
'Weighted Precision': 0.262093400652312,
'Micro Precision': 0.22372881355932203,
'Macro Precision': 0.23832568829432801}