README.md

---
language:
- ru
library_name: nemo
dataset:
- mozilla-foundation/common_voice_10_0
- SberDevices/Golos
- Russian LibriSpeech
- SOVA Dataset
thumbnail: null
tags:
- automatic-speech-recognition
- speech
- audio
- Transducer
- Conformer
- Transformer
- pytorch
- NeMo
- hf-asr-leaderboard
license: cc-by-4.0
model-index:
- name: stt_ru_conformer_transducer_large
  results:
  - task:
      type: Automatic Speech Recognition
      name: automatic-speech-recognition
    dataset:
      name: Mozilla Common Voice 10.0
      type: mozilla-foundation/common_voice_10_0
      config: ru
      split: test
      args:
        language: ru
    metrics:
    - name: Test WER
      type: wer
      value: 3.96
  - task:
      type: Automatic Speech Recognition
      name: automatic-speech-recognition
    dataset:
      name: Mozilla Common Voice 10.0
      type: mozilla-foundation/common_voice_10_0
      config: ru
      split: dev
      args:
        language: ru
    metrics:
    - name: Test WER
      type: wer
      value: 3.49
  - task:
      type: Automatic Speech Recognition
      name: automatic-speech-recognition
    dataset:
      name: Sberdevices Golos (crowd)
      type: SberDevices/Golos
      config: crowd
      split: test
      args:
        language: ru
    metrics:
    - name: Test WER
      type: wer
      value: 2.65
  - task:
      type: Automatic Speech Recognition
      name: automatic-speech-recognition
    dataset:
      name: Sberdevices Golos (farfield)
      type: SberDevices/Golos
      config: farfield
      split: test
      args:
        language: ru
    metrics:
    - name: Test WER
      type: wer
      value: 7.56
  - task:
      type: Automatic Speech Recognition
      name: automatic-speech-recognition
    dataset:
      name: Russian LibriSpeech
      type: RuLS
      config: ru
      split: test
      args:
        language: ru
    metrics:
    - name: Test WER
      type: wer
      value: 11.95
---
# NVIDIA Conformer-Transducer Large (Russian)

<style>
img {
 display: inline;
}
</style>

| [![Model architecture](https://img.shields.io/badge/Model_Arch-Conformer--Transducer-lightgrey#model-badge)](#model-architecture)
| [![Model size](https://img.shields.io/badge/Params-120M-lightgrey#model-badge)](#model-architecture)
| [![Language](https://img.shields.io/badge/Language-rw-lightgrey#model-badge)](#datasets)