Instructions to use parambharat/whisper-tiny-south-indic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use parambharat/whisper-tiny-south-indic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="parambharat/whisper-tiny-south-indic")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("parambharat/whisper-tiny-south-indic") model = AutoModelForSpeechSeq2Seq.from_pretrained("parambharat/whisper-tiny-south-indic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add multilingual to the language tag
#1
by lbourdois - opened
Hi! A PR to add multilingual to the language tag to improve the referencing.
parambharat changed pull request status to merged