Spaces:
Runtime error
Runtime error
File size: 2,138 Bytes
409b791 fafbc3d 409b791 f4da052 409b791 0eab03f 409b791 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
from transformers import AutoModelForSequenceClassification, AutoTokenizer, Trainer
import gradio as gr
import torch
import numpy as np
from mapping_labels import languages_map, id2label
model_checkpoint = "dinalzein/xlm-roberta-base-finetuned-language-identification"
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint, use_fast=True)
model = AutoModelForSequenceClassification.from_pretrained(model_checkpoint)
trainer = Trainer(model)
class Dataset(torch.utils.data.Dataset):
def __init__(self, encodings, labels=None):
self.encodings = encodings
self.labels = labels
def __getitem__(self, idx):
item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
if self.labels:
item["labels"] = torch.tensor(self.labels[idx])
return item
def __len__(self):
return len(self.encodings["input_ids"])
def identify_language(txt):
txt=[txt]
tokenized_txt = tokenizer(txt, truncation=True, max_length=20)
txt_dataset = Dataset(tokenized_txt)
raw_pred, _, _ = trainer.predict(txt_dataset)
# Preprocess raw predictions
y_pred = np.argmax(raw_pred, axis=1)
return languages_map[id2label[str(y_pred[0])]]
#with gr.Row():
examples = [
"C'est La Vie",
"So ist das Leben",
"That is life",
"ΩΨ°Ω ΩΩ Ψ§ΩΨΩΨ§Ψ©"
]
inputs=gr.inputs.Textbox(placeholder="Enter your text here", label="Text content", lines=5)
outputs=gr.outputs.Label(label="Language Identified:")
article = ('''## Suppoted Langauges \n
Arabic (ar), Bulgarian (bg), German (de), Modern greek (el), English (en), Spanish (es), French (fr), Hindi (hi), Italian (it), Japanese (ja), Dutch (nl), Polish (pl), Portuguese (pt), Russian (ru), Swahili (sw), Thai (th), Turkish (tr), Urdu (ur), Vietnamese (vi), Chinese (zh)
''')
gr.Interface(
fn=identify_language,
inputs=inputs,
outputs=outputs,
verbose=True,
examples = examples,
title="Language Identifier",
description="It aims at identifing the language a document is written in. It supports 20 different languages.",
article=article,
theme="huggingface"
).launch()
|