README.md

metadata

language:
  - uz
license: apache-2.0
tags:
  - audio
  - automatic-speech-recognition
  - speech
  - sherpa-onnx
  - vosk
datasets:
  - issai/Uzbek_Speech_Corpus
  - fsicoli/common_voice_22_0
  - DavronSherbaev/uzbekvoice
metrics:
  - wer
pipeline_tag: automatic-speech-recognition
model-index:
  - name: Vosk Uzbek Small Speech Recognition Model
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: FLEURS Uzbek
          type: google/fleurs
          config: uz_uz
          split: test
        metrics:
          - type: wer
            value: 17.67
            name: Test WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: issai/Uzbek_Speech_Corpus
          type: issai/Uzbek_Speech_Corpus
          split: test
        metrics:
          - type: wer
            value: 15.42
            name: Test WER

Vosk Uzbek Speech Recognition Model

Uzbek automatic speech recognition (ASR) model for sherpa-onnx. Architecture is non-streaming Zipformer2.

Version 0.60

Training Data

This model was trained on CommonVoice, ISSAI USC and Uzvoice