ARTPARK-IISc/whisper-large-v3-vaani-odia

import torch
from transformers import pipeline

audio = "path to the audio file to be transcribed"
device = "cuda:0" if torch.cuda.is_available() else "cpu"
modelTags = "ARTPARK-IISc/whisper-large-v3-vaani-odia"

transcribe = pipeline(
    task="automatic-speech-recognition",
    model=modelTags,
    chunk_length_s=30,
    device=device
)


transcribe.model.config.forced_decoder_ids = None
transcribe.model.generation_config.forced_decoder_ids = None

print("Transcription:", transcribe(audio)["text"])

@misc{pulikodan2026vaanicapturinglanguagelandscape,
      title={VAANI: Capturing the language landscape for an inclusive digital India}, 
      author={Sujith Pulikodan and Abhayjeet Singh and Agneedh Basu and Nihar Desai and Pavan Kumar J and Pranav D Bhat and Raghu Dharmaraju and Ritika Gupta and Sathvik Udupa and Saurabh Kumar and Sumit Sharma and Vaibhav Vishwakarma and Visruth Sanka and Dinesh Tewari and Harsh Dhand and Amrita Kamat and Sukhwinder Singh and Shikhar Vashishth and Partha Talukdar and Raj Acharya and Prasanta Kumar Ghosh},
      year={2026},
      eprint={2603.28714},
      archivePrefix={arXiv},
      primaryClass={eess.AS},
      url={https://arxiv.org/abs/2603.28714}, 
}