xls-r-uzbek-cv8 / README.md
lucio's picture
update model card
6a65d17
metadata
language:
  - uz
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_8_0
  - generated_from_trainer
  - robust-speech-event
datasets:
  - mozilla-foundation/common_voice_8_0
model-index:
  - name: XLS-R-300M Uzbek CV8
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 8
          type: mozilla-foundation/common_voice_8_0
          args: uz
        metrics:
          - name: Test WER
            type: wer
            value: 40.56
          - name: Test CER
            type: cer
            value: 8.25

XLS-R-300M Uzbek CV8

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - UG dataset.

Model description

For a description of the model architecture, see facebook/wav2vec2-xls-r-300m

The model vocabulary consists of the Modern Latin alphabet for Uzbek, with punctuation removed. Note that the characters ‘ and ’ do not count as punctuation, as ‘ modifies and

Intended uses & limitations

This model is expected to be of some utility for low-fidelity use cases such as:

  • Draft video captions
  • Indexing of recorded broadcasts

The model is not reliable enough to use as a substitute for live captions for accessibility purposes, and it should not be used in a manner that would infringe the privacy of any of the contributors to the Common Voice dataset nor any other speakers.

Training and evaluation data

The 30% of the train common voice official split was used as training data. The half of the official dev split was used as validation data, and the full test set was used for final evaluation.

Framework versions

  • Transformers 4.17.0.dev0
  • Pytorch 1.10.2+cu102
  • Datasets 1.18.3
  • Tokenizers 0.11.0