sagorhishab's picture
Update README.md
ab49101
|
raw
history blame
680 Bytes
metadata
license: cc-by-nc-4.0
language:
  - bn
library_name: nemo
pipeline_tag: automatic-speech-recognition

Hishab BN FastConformer

Hishab BN FastConformer is a fastconformer based model trained on 18k MegaBNSpeech corpus.

Using method

To use this model you need to install NeMo.

Inferencing

import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.ASRModel.from_pretrained("hishab/hishab_bn_fastconformer")

transcriptions = asr_model.transcribe(["file.wav"])

Training Datasets

Training Details