Swecha Telugu ASR

Model Overview

This model is a fine-tuned version of OpenAI Whisper Tiny for Telugu Automatic Speech Recognition (ASR).

Base Model

  • openai/whisper-tiny

Language

  • Telugu (te)

Dataset

  • Mozilla Common Voice Telugu

Training

  • Fine-tuned using the Mozilla AI Speech-to-Text Fine-tuning Blueprint.
  • Framework: Hugging Face Transformers
  • Platform: Google Colab

Intended Use

  • Telugu speech recognition
  • Voice assistants
  • Accessibility applications
  • Research and educational purposes

Acknowledgements

  • Swecha
  • Mozilla AI
  • Mozilla Common Voice
  • Hugging Face
  • OpenAI Whisper
Downloads last month
28
Safetensors
Model size
37.8M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for eedulakantijashwitha/swecha-commonvoice-telugu-asr

Finetuned
(1885)
this model