YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

langid-mmbert-small-8gpu

Language identification model based on jhu-clsp/mmBERT-small for 14 classes:

• ko, no, da, sv, fi, nl, en, fr, de, es, pt, it, ja
• UNKNOWN

Inference Guide

This project supports two inference styles:

1. pipeline("text-classification") for quick usage.
2. AutoTokenizer + AutoModelForSequenceClassification for explicit forward-pass control.

Both can use a fast UNKNOWN pre-check:

import re

URL_PATTERN = re.compile(r"https?://\S+|www\.\S+", flags=re.IGNORECASE)

def fast_detect_unknown(text: str) -> bool:
 s = text.strip()
 if not s:
 # Empty input is treated as non-language.
 return True
 if URL_PATTERN.search(s):
 # URLs should map to UNKNOWN.
 return True

 total = len(s)
 alpha = sum(ch.isalpha() for ch in s)
 digits = sum(ch.isdigit() for ch in s)
 spaces = sum(ch.isspace() for ch in s)
 symbols = total - alpha - digits - spaces
 non_space = max(1, total - spaces)

 # Mostly numeric strings (ids, phone numbers, etc.).
 if digits / non_space >= 0.8:
 return True
 # Symbol-heavy text is usually not valid language content.
 if symbols / non_space >= 0.45:
 return True
 # Very low alphabetic ratio indicates gibberish-like input.
 if total >= 6 and (alpha / non_space) < 0.2:
 return True
 # Long compact mixed tokens often represent hashes/usernames/keys.
 if " " not in s and total >= 12 and (alpha / non_space) < 0.45 and (digits > 0 or symbols > 0):
 return True
 return False

Option A: Pipeline

import torch
from transformers import pipeline

model_id = "chiennv/langid-mmbert-small"
device = 0 if torch.cuda.is_available() else -1
clf = pipeline(
 "text-classification",
 model=model_id,
 tokenizer=model_id,
 top_k=1,
 device=device, # GPU id (0,1,...) or -1 for CPU
)

text = "Bonjour tout le monde"
if fast_detect_unknown(text):
 print({"label": "UNKNOWN", "score": 1.0})
else:
 out = clf(text)[0][0]
 print({"label": out["label"], "score": round(out["score"], 4)})

Option B: AutoModelForSequenceClassification Only

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_id = "chiennv/langid-mmbert-small"
tokenizer = AutoTokenizer.from_pretrained(model_id)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Use FP16 on GPU for faster inference and lower memory.
dtype = torch.float16 if device.type == "cuda" else torch.float32
model = AutoModelForSequenceClassification.from_pretrained(model_id, torch_dtype=dtype).to(device)
model.eval()

text = "Bonjour tout le monde"
if fast_detect_unknown(text):
 print({"label": "UNKNOWN", "score": 1.0})
else:
 inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
 inputs = {k: v.to(device) for k, v in inputs.items()}
 with torch.no_grad():
 logits = model(**inputs).logits
 probs = torch.softmax(logits, dim=-1).squeeze(0)
 pred_id = int(torch.argmax(probs).item())
 pred_label = model.config.id2label[pred_id]
 pred_score = float(probs[pred_id].item())
 print({"label": pred_label, "score": round(pred_score, 4)})

Run local infer.py

python infer.py

GPU Notes

• Check CUDA availability:
  • python -c "import torch; print(torch.cuda.is_available(), torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'no-gpu')"
• The AutoModel example above automatically uses GPU + FP16 when CUDA is available.