Spaces:
Running
Running
| from transformers import AutoModelForSequenceClassification | |
| from transformers import AutoTokenizer | |
| import numpy as np | |
| from scipy.special import softmax | |
| MODEL = "Davlan/naija-twitter-sentiment-afriberta-large" | |
| tokenizer = AutoTokenizer.from_pretrained(MODEL) | |
| # PT | |
| model = AutoModelForSequenceClassification.from_pretrained(MODEL) | |
| def get_senti(text): | |
| encoded_input = tokenizer(text, return_tensors='pt') | |
| output = model(**encoded_input) | |
| scores = output[0][0].detach().numpy() | |
| scores = softmax(scores) | |
| id2label = {0:"positive✅", 1:"neutral😐", 2:"negative❌"} | |
| ranking = np.argsort(scores) | |
| ranking = ranking[::-1] | |
| out = [] | |
| for i in range(scores.shape[0]): | |
| l = id2label[ranking[i]] | |
| s = scores[ranking[i]] | |
| out.append(f"{i+1}) {l} {np.round(float(s), 4)}") | |
| out.append('\nNOTE: "The higher the values, the higher the sentiment for that class & vice-versa"') | |
| return "\n".join(out) | |
| import gradio as gr | |
| demo = gr.Interface( | |
| fn=get_senti, | |
| inputs=gr.Textbox(lines=2, placeholder="Enter Words Here (Igbo, Yoruba, Hausa Pidgin)..."), | |
| outputs="text", | |
| ) | |
| demo.launch() |