---
language:
  - tg
license: apache-2.0
tags:
  - audio
  - automatic-speech-recognition
  - speech
  - sherpa-onnx
  - vosk
datasets:
  - Peacockery/tajik-asr-corpus-v3
metrics:
  - wer
pipeline_tag: automatic-speech-recognition
model-index:
  - name: Vosk Tajik Speech Recognition Model
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: FLEURS Tajik
          type: google/fleurs
          config: tg_tj
          split: test
        metrics:
          - type: wer
            value: 13.85
            name: Test WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Peacockery/tajik-asr-corpus-v3
          type: Peacockery/tajik-asr-corpus-v3
          split: test
        metrics:
          - type: wer
            value: 28.21
            name: Test WER
---

# Vosk Tajik Speech Recognition Model

Tajik automatic speech recognition (ASR) model for [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx). Architecture is non-streaming Zipformer2.

Version 0.61

## Word Error Rate (WER)

| Dataset | WER |
|---------|-----|
| [FLEURS Tajik](https://huggingface.co/datasets/google/fleurs) | 13.85 |
| [Peacockery/tajik-asr-corpus-v3](https://huggingface.co/datasets/Peacockery/tajik-asr-corpus-v3) (test split) | 28.21 |

## Training Data

This model was trained on [Peacockery/tajik-asr-corpus-v3](https://huggingface.co/datasets/Peacockery/tajik-asr-corpus-v3).