Instructions to use MERaLiON/MERaLiON-SER-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MERaLiON/MERaLiON-SER-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="MERaLiON/MERaLiON-SER-v1", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MERaLiON/MERaLiON-SER-v1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
The model loading process requires the config file of openai/whisper-medium
The model loading process requires the config file of openai/whisper-medium, but it is not included in the downloaded model directory. Therefore, you need to download the config separately from openai/whisper-medium.
"model_type": "ser-whisper-ecapa",
"num_emotions": 7,
"pooling_type": "hybrid",
"sampling_rate": 16000,
"torch_dtype": "float32",
"transformers_version": "4.49.0",
"use_weighted_sum": false,
"whisper_name": "openai/whisper-medium"
Thanks for your interest in the model. This may be due to different version of transformer lib. The example worked well and it downloads all the required models and config. I tested with transformers version 4.46.3, however, it should work on any new transformer lib package as well.