Instructions to use mlaricheva/roberta-psych with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlaricheva/roberta-psych with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="mlaricheva/roberta-psych")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("mlaricheva/roberta-psych") model = AutoModelForMaskedLM.from_pretrained("mlaricheva/roberta-psych") - Notebooks
- Google Colab
- Kaggle
roberta-psych
language: en
This is a RoBERTa model pretrained on Alexander Street Database of Counselling and Psychotherapy Transcripts (see more about database and its content here).
Further information about training, parameters and evaluation is available in our paper:
Laricheva, M., Zhang, C., Liu, Y., Chen, G., Tracey, T., Young, R., & Carenini, G. (2022). Automated Utterance Labeling of Conversations Using Natural Language Processing. arXiv preprint arXiv:2208.06525