ilprl-docse/NwachaMuna-NepConformer-FT

Nwāchā Munā NepConformer Finetune

NwachaMuna-NepConformer-FT. This model was trained as part of the paper Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR. It is a NepConformer fine-tuned model on the Nwāchā Munā corpus — achieving 18.72% CER. The training scripts of this model can be found at https://github.com/ilprl/nwacha-muna.

Usage

import nemo.collections.asr as nemo_asr
model = nemo_asr.models.ASRModel.from_pretrained("ilprl-docse/NwachaMuna-NepConformer-FT")

transcriptions = model.transcribe(["file.wav"])
print(transcriptions[0])