Parakeet CTC 0.6B - Fine-tuned on Children's Speech

Fine-tuned from nvidia/parakeet-ctc-0.6b on children's speech data from the DrivenData ASR competition.

Training config

  • Mode: full
  • Epochs: 10
  • Batch size: 16 (accumulate: 2)
  • Learning rate: 3e-05
  • Precision: bf16-mixed
  • Speed perturbation: True

Usage

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)
Downloads last month
24
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Phaedrus33/parakeet-ctc-0.6b-children

Finetuned
(8)
this model