Shrutam-2

<div align="center"> <img src="https://huggingface.co/bharatgenai/Shrutam-2/resolve/main/BharatGen_Logo.png" width="60%" alt="BharatGen" /> </div> <hr> <div align="center"> <a href="https://huggingface.co/bharatgenai/Shrutam-2/blob/main/LICENSE" target="_blank" style="margin: 4px;"> <img alt="License" src="https://img.shields.io/badge/License-BharatGen%20Non--Commercial-yellow.svg" /> </a> </div>

Shrutam-2: LLM-Powered Multilingual Indic Speech Recognition

Shrutam-2 is a LLM based automatic speech recognition system for 12 major Indian languages. It bridges a Conformer speech encoder with a pretrained LLM decoder through a Mixture-of-Experts (MoE) projection layer, enabling high-quality, prompt-controllable transcription across diverse Indic languages.

Architecture Overview

Unlike conventional CTC/Attention ASR systems that map audio directly to text tokens, Shrutam-2 reframes speech recognition as a conditional language generation task. A speech encoder produces frame-level audio representations, which are then projected into the LLM's embedding space and fed to a frozen LLM decoder alongside a text prompt.

Languages Supported

Usage

1. Create virtual env

conda create -n shrutam2 python=3.10.14
conda activate shrutam2

2. Install dependencies

pip install torch==2.3.0 torchvision==0.18.0 torchaudio==2.3.0 --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txt

3. Run inference

from transformers import AutoModel, AutoTokenizer
import torch

REPO_ID = "bharatgenai/Shrutam-2"

model = AutoModel.from_pretrained(REPO_ID, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(REPO_ID)
model.to("cuda" if torch.cuda.is_available() else "cpu")
model.eval()

prompt = "Transcribe speech to Hindi text."

# Single file (non-16 kHz audio is resampled automatically)
print(model.transcribe("audio.wav", prompts=prompt, tokenizer=tokenizer))

# Batch inference — one prompt per file
wavs = ["clip_hi.wav", "clip_mr.wav", "clip_ta.wav"]
prompts = [
    "Transcribe speech to Hindi text.",
    "Transcribe speech to Marathi text.",
    "Transcribe speech to Tamil text.",
]
print(model.transcribe(wavs, prompts=prompts, batch_size=2, tokenizer=tokenizer))

License

This model is released under the BharatGen non-commercial license. Please refer to the LICENSE file for detailed terms and conditions.

Shrutam 2 is developed based on the research outlined in the paper-<a href="https://arxiv.org/abs/2601.19451">https://arxiv.org/abs/2601.19451</a>