Add e9 interface

interfaces/emotion9.py

@@ -0,0 +1,56 @@
+import gradio as gr
+
+import os
+import torch
+import numpy as np
+from transformers import AutoModelForSequenceClassification
+from transformers import AutoTokenizer
+from huggingface_hub import HfApi
+
+from label_dicts import EMOTION9_LABEL_NAMES
+
+HF_TOKEN = os.environ["hf_read"]
+
+languages = [
+    "Czech", "English", "German", "Hungarian", "Polish", "Slovak"
+]
+domains = {
+    "parliamentary speech": "parlspeech",
+}
+
+def build_huggingface_path(language: str):
+    language = language.lower()
+    return f"poltextlab/xlm-roberta-large-pooled-{language}-emotions9"
+
+def predict(text, model_id, tokenizer_id):
+    device = torch.device("cpu")
+    model = AutoModelForSequenceClassification.from_pretrained(model_id, low_cpu_mem_usage=True, device_map="auto", offload_folder="offload", token=HF_TOKEN)
+    tokenizer = AutoTokenizer.from_pretrained(tokenizer_id)
+    model.to(device)
+
+    inputs = tokenizer(text,
+                       max_length=512,
+                       truncation=True,
+                       padding="do_not_pad",
+                       return_tensors="pt").to(device)
+    model.eval()
+
+    with torch.no_grad():
+        logits = model(**inputs).logits
+
+    NUMS_DICT = {i: key for i, key in enumerate(sorted(EMOTION9_LABEL_NAMES.keys()))}
+    output_pred = {f"[{NUMS_DICT[i]}] {EMOTION9_LABEL_NAMES[NUMS_DICT[i]]}": probs[i] for i in np.argsort(probs)[::-1]}
+    output_info = f'<p style="text-align: center; display: block">Prediction was made using the <a href="https://huggingface.co/{model_id}">{model_id}</a> model.</p>'
+    return output_pred, output_info
+
+def predict_e6(text, language, domain):
+    model_id = build_huggingface_path(language)
+    tokenizer_id = "xlm-roberta-large"
+    return predict(text, model_id, tokenizer_id)
+
+demo = gr.Interface(
+    fn=predict_e6,
+    inputs=[gr.Textbox(lines=6, label="Input"),
+            gr.Dropdown(languages, label="Language"),
+            gr.Dropdown(domains.keys(), label="Domain")],
+    outputs=[gr.Label(num_top_classes=5, label="Output"), gr.Markdown()])