Modelpublic

Phaedrus33/nemotron-speech-streaming-children-v17

sourceHugging Facecc-by-4.0updated 6mo agoView on Hugging Face

0likes33downloads

Model Card

nemotron-speech-streaming-en-0.6b - Fine-tuned on Children's Speech

Fine-tuned from nvidia/nemotron-speech-streaming-en-0.6b on children's speech data from the DrivenData ASR competition.

Training config

—Mode: full
—Epochs: 5
—Batch size: 16 (accumulate: 2)
—Learning rate: 1e-05
—Precision: bf16-mixed
—Speed perturbation: True

Usage

python

import nemo.collections.asr as nemo_asr

model = nemo_asr.models.ASRModel.restore_from("best_model.nemo")
hypotheses = model.transcribe(["audio.flac"])
print(hypotheses[0].text)