metadata
language:
- as
- bn
- brx
- doi
- gu
- hi
- kn
- kok
- ks
- mai
- ml
- mni
- mr
- ne
- or
- pa
- sa
- sat
- sd
- ta
- te
- ur
pipeline_tag: automatic-speech-recognition
library_name: transformers
pip install -q torch_state_bridge srt webrtcvad torchcodec
from transformers import AutoModel
model = AutoModel.from_pretrained("shethjenil/Indic-STT", language="hi", trust_remote_code=True, dtype="auto")
wav , sr = torchaudio.load("audio.wav")
for i in model.transcribe(wav,sr,4):
print("".join(i.splitlines()[2::4]).replace("▁"," ").replace("<line>","\n"))
full_model = AutoModel.from_pretrained("shethjenil/Indic-STT", trust_remote_code=True, dtype="auto")
full_model.language = "hi"