LLM-Hindi-Large

---

language:

• hi license: apache-2.0 tags:
• whisper-event metrics:
• wer model-index:
• name: LLM-HINDI-LARGE - Manan Raval results:
  • task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: google/fleurs type: google/fleurs config: hn_in split: test metrics:
    • type: wer value: 12.33 name: WER

Usage

In order to infer a single audio file using this model, the following code snippet can be used:

>>> import torch
>>> from transformers import pipeline

>>> # path to the audio file to be transcribed
>>> audio = "/path/to/audio.format"
>>> device = "cuda:0" if torch.cuda.is_available() else "cpu"

>>> transcribe = pipeline(task="automatic-speech-recognition", model="web30india/LLM-Hindi-Large", chunk_length_s=30, device=device)
>>> transcribe.model.config.forced_decoder_ids = transcribe.tokenizer.get_decoder_prompt_ids(language="hi", task="transcribe")

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

Acknowledgement

This work was done at [Virtual Height IT Services Pvt. Ltd.]