Automatic Speech Recognition
NeMo
Ukrainian
Eval Results
theodotus's picture
Added half-finished trainian run
a5a3eac
metadata
language:
  - uk
library_name: nemo
datasets:
  - mozilla-foundation/common_voice_10_0
  - Yehor/voa-uk-transcriptions
tags:
  - automatic-speech-recognition
model-index:
  - name: stt_uk_contextnet_512
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Mozilla Common Voice 10.0
          type: mozilla-foundation/common_voice_10_0
          config: clean
          split: test
          args:
            language: uk
        metrics:
          - name: Test WER
            type: wer
            value: 7.59
license: bsd-3-clause

NVIDIA ContextNet 512 (uk-UA)

| Model architecture | Model size | Language |

Attribution

As initial checkpoint used stt_en_contextnet_512 by NVIDIA licensed under CC-BY-4.0