Multimodal Classification Model (Tamil, Malayalam, Telugu)

This repository contains deep learning models for text and audio classification in three languages: Tamil, Malayalam, and Telugu.

📌 Overview

The models accept text and audio inputs and classify them into predefined categories. Each language has dedicated trained models and label encoders:

Text Model: Utilizes xlm-roberta-large for feature extraction with a deep learning classifier.
Audio Model: Uses MFCC feature extraction and a CNN-based classifier.

🛠 1. Setup

1.1 Clone the Repository

git clone https://huggingface.co/<your-model-repo>
cd <your-model-repo>

1.2 Install Dependencies

Ensure Python is installed, then run:

pip install -r requirements.txt

📂 2. Directory Structure

├── audio_label_encoders/       # Label encoders for audio models
├── audio_models/               # Trained audio classification models
├── text_label_encoders/        # Label encoders for text models
└── text_models/                # Trained text classification models

Each folder contains three files, corresponding to Tamil, Malayalam, and Telugu.

🚀 3. How to Use

3.1 Load the Models

import tensorflow as tf
import pickle
import numpy as np
import torch
from transformers import AutoTokenizer, AutoModel

# Load Label Encoders
with open("text_label_encoders/tamil_label_encoder.pkl", "rb") as f:
    tamil_text_label_encoder = pickle.load(f)

with open("audio_label_encoders/tamil_audio_label_encoder.pkl", "rb") as f:
    tamil_audio_label_encoder = pickle.load(f)

# Load Models
text_model = tf.keras.models.load_model("text_models/tamil_text_model.h5")
audio_model = tf.keras.models.load_model("audio_models/tamil_audio_model.keras")

📝 4. Text Classification

4.1 Preprocess Text

from indicnlp.tokenize import indic_tokenize
from indicnlp.normalize.indic_normalize import IndicNormalizerFactory
import advertools as adv

stopwords = list(sorted(adv.stopwords["tamil"]))

def preprocess_tamil_text(text):
    tokens = list(indic_tokenize.trivial_tokenize(text, lang="ta"))
    tokens = [token for token in tokens if token not in stopwords]
    return " ".join(tokens)

4.2 Extract Features and Predict

def extract_embeddings(model_name, texts):
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModel.from_pretrained(model_name)
    model.eval()
    
    embeddings = []
    batch_size = 16
    with torch.no_grad():
        for i in range(0, len(texts), batch_size):
            batch_texts = texts[i:i + batch_size]
            encoded_inputs = tokenizer(batch_texts, padding=True, truncation=True, max_length=128, return_tensors="pt")
            outputs = model(**encoded_inputs)
            batch_embeddings = outputs.last_hidden_state.mean(dim=1).numpy()
            embeddings.extend(batch_embeddings)
    return np.array(embeddings)

feature_extractor = "xlm-roberta-large"
text = "உங்கள் உதவி மிகவும் பயனுள்ளதாக இருந்தது"
processed_text = preprocess_tamil_text(text)
text_embeddings = extract_embeddings(feature_extractor, [processed_text])

text_predictions = text_model.predict(text_embeddings)
predicted_label = tamil_text_label_encoder.inverse_transform(np.argmax(text_predictions, axis=1))
print("Predicted Label:", predicted_label[0])

🔊 5. Audio Classification

5.1 Preprocess Audio

import librosa

def extract_audio_features(file_path, sr=22050, n_mfcc=40):
    audio, _ = librosa.load(file_path, sr=sr)
    mfccs = librosa.feature.mfcc(y=audio, sr=sr, n_mfcc=n_mfcc)
    return np.mean(mfccs.T, axis=0)

5.2 Predict Audio Class

def predict_audio(file_path):
    features = extract_audio_features(file_path)
    reshaped_features = features.reshape((1, 40, 1, 1))
    predicted_class = np.argmax(audio_model.predict(reshaped_features), axis=1)
    predicted_label = tamil_audio_label_encoder.inverse_transform(predicted_class)
    return predicted_label[0]

audio_file = "test_audio.wav"
predicted_audio_label = predict_audio(audio_file)
print("Predicted Audio Label:", predicted_audio_label)

📊 6. Batch Processing for a Dataset

6.1 Load Dataset

import os
import pandas as pd

def load_dataset(base_dir='../test', lang='tamil'):
    dataset = []
    lang_dir = os.path.join(base_dir, lang)
    audio_dir = os.path.join(lang_dir, "audio")
    text_dir = os.path.join(lang_dir, "text")
    
    text_file = os.path.join(text_dir, [file for file in os.listdir(text_dir) if file.endswith(".xlsx")][0])
    text_df = pd.read_excel(text_file)

    for file in text_df["File Name"]:
        if (file + ".wav") in os.listdir(audio_dir):
            audio_path = os.path.join(audio_dir, file + ".wav")
            transcript_row = text_df.loc[text_df["File Name"] == file]
            transcript = transcript_row.iloc[0]["Transcript"] if not transcript_row.empty else ""
            dataset.append({"File Name": audio_path, "Transcript": transcript})
        else:
            transcript_row = text_df.loc[text_df["File Name"] == file]
            transcript = transcript_row.iloc[0]["Transcript"] if not transcript_row.empty else ""
            dataset.append({"File Name": "Nil", "Transcript": transcript})
    
    return pd.DataFrame(dataset)

dataset_df = load_dataset()

6.2 Predict Text and Audio in Bulk

dataset_df["Transcript"] = dataset_df["Transcript"].apply(preprocess_tamil_text)
text_embeddings = extract_embeddings(feature_extractor, dataset_df["Transcript"].tolist())
text_predictions = text_model.predict(text_embeddings)
text_labels = tamil_text_label_encoder.inverse_transform(np.argmax(text_predictions, axis=1))

dataset_df["Predicted Text Label"] = text_labels
dataset_df["Predicted Audio Label"] = dataset_df["File Name"].apply(lambda x: predict_audio(x) if x != "Nil" else "No Audio")
dataset_df.to_csv("predictions.tsv", sep="\t", index=False)

☁️ 7. Deployment on Hugging Face

pip install huggingface_hub
huggingface-cli login

from huggingface_hub import upload_file

upload_file(path_or_fileobj="text_models/tamil_text_model.h5", path_in_repo="text_models/tamil_text_model.h5", repo_id="<your-hf-repo>")

📬 Contact

For issues or improvements, feel free to raise an issue or email [email protected].

License: CC BY-NC 4.0

vasantharan
/

Multimodal_Hate_Speech_Detection_in_Dravidian_languages