---
library_name: transformers
base_model: google/muril-base-cased
tags:
  - language-identification
  - indian-languages
  - banking
  - romanized
language:
  - en
  - hi
  - bn
  - ta
  - te
  - kn
  - ml
  - mr
  - gu
  - pa
  - ur
  - or
  - as
  - ne
  - sa
  - sd
  - ks
license: apache-2.0
---

# muril-lang-id-v7

Fine-tuned [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) for language identification on Indian banking chatbot messages. Covers 17 Indian languages plus English in both native and Romanized script, with an 18th `undetermined` class for out-of-distribution inputs.

This is v7 of an iterative series ([v1](https://huggingface.co/dnivra26/muril-lang-id-v1) → [v6](https://huggingface.co/dnivra26/muril-lang-id-v6)). v7 adds brand-laden English banking Q&A, expanded Dravidian Romanized templates, and banking-style European OOD to the v6 training mix.

## Labels (0–17)

`as`, `bn`, `en`, `gu`, `hi`, `kn`, `ks`, `ml`, `mr`, `ne`, `or`, `pa`, `sa`, `sd`, `ta`, `te`, `ur`, `undetermined`

## Evaluation

On a held-out 1882-row banking chat test set:

| version | overall | en | hi | kn | ta | te | undetermined |
|---------|---------|----|----|----|----|----|---|
| v5 | 91.82% | 98.2% | 99.7% | 91.6% | 81.3% | 80.5% | 77.8% |
| v6 | 93.25% | 96.0% | 99.8% | 97.5% | 92.4% | 78.8% | 82.5% |
| **v7** | **96.07%** | **100%** | **99.8%** | **99.2%** | **97.9%** | **93.8%** | **84.0%** |

Held-out stratified test (from the training-mix distribution): accuracy 0.9731, f1_macro 0.9675.

## Usage

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

repo = "dnivra26/muril-lang-id-v7"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSequenceClassification.from_pretrained(repo)
model.eval()

LABELS = ["as","bn","en","gu","hi","kn","ks","ml","mr","ne","or","pa","sa","sd","ta","te","ur","undetermined"]
ENERGY_THRESHOLD = -7.0  # energy > threshold ⇒ flag as undetermined

text = "mera balance kitna hai"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
with torch.inference_mode():
    logits = model(**inputs).logits.squeeze(0)
energy = -torch.logsumexp(logits, dim=0).item()
top = int(logits.argmax())
label = "undetermined" if energy > ENERGY_THRESHOLD else LABELS[top]
print(label)  # → hi
```

## Training

- **Base:** google/muril-base-cased
- **Epochs:** 3
- **Batch size:** 128, **lr:** 4e-5, **precision:** bf16 + TF32
- **Max seq length:** 128
- **Datasets:** AI4Bharat Bhasha-Abhijnaanam, AI4Bharat Aksharantar, SST-2, suhani-sarvam/google-dakshina, findnitai/english-to-hinglish, AmazonScience/MASSIVE, community-datasets/offenseval_dravidian (non-offensive only), bitext retail-banking, FLORES-200 (OOD), synthetic brand-laden English banking Q&A, banking-style European OOD (DE/FR/PT/ES/IT/TR/SV/NL), synthetic gibberish.

## Notes

- Romanized Urdu and Hindi are merged to `hi` at inference time (Hindustani is effectively one spoken language).
- Pre-v6 checkpoints in this series only emit labels 0–16 and need a tighter energy threshold (`-11.22`).
- Works best when wrapped in a pipeline that runs Unicode-script short-circuiting first, so deterministic native-script inputs skip the model entirely.