Downloads · 30 days
7
2% of all-time downloads
hr-elrond/autotrain-consumer-nature-speech_finbert-2147169289
autotrain-consumer-nature-speech_finbert-2147169289 is a text classification model from hr-elrond. Use it when you need a label for a piece of text. It is set up for transformers.
We trained FinBERT to identify whether firms´ talk contains consumer concepts of human nature (e.g., "I believe consumers generally act rational.", "Consumers must take over responsibility for the choices they make.",…
Downloads · 30 days
7
2% of all-time downloads
All-time downloads
421
Public
Repo size
879 MB
Likes
2
Public
Click a slice to open those files.
.bin439 MB · 100%
From the Hugging Face model README
We trained FinBERT to identify whether firms´ talk contains consumer concepts of human nature (e.g., "I believe consumers generally act rational.", "Consumers must take over responsibility for the choices they make.", "It seems consumers behave quite altruistic.") from statements that do not (e.g., "We expect buyers to double their purchases next year.", "We see a 5% growth in numbers compared to the previous year.").
The training data consisted of 236 positive documents (containing concepts of consumer nature) and 1034 negative documents (not contain concepts of consumer nature) extracted from earnings call transcripts of S&P-500 companies (2015-2020).
You can use cURL to access this model:
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/hr-elrond/autotrain-consumer-nature-speech_finbert-2147169289
Or Python API:
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("hr-elrond/autotrain-consumer-nature-speech_finbert-2147169289", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("hr-elrond/autotrain-consumer-nature-speech_finbert-2147169289", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)