openslr/openslr
Updated • 520 • 31
How to use kasunw/whisper-large-v3-sinhala with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="kasunw/whisper-large-v3-sinhala") # Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("kasunw/whisper-large-v3-sinhala")
model = AutoModelForSpeechSeq2Seq.from_pretrained("kasunw/whisper-large-v3-sinhala", device_map="auto")This is a finetuned version of the aforementioned base model for Sinhala Speech Recognition using the openslr dataset.
Usage sample can be checked here.