---
language:
- ru
license: apache-2.0
tags:
- automatic-speech-recognition
- ru
datasets:
- mozilla-foundation/common_voice_7_0
---
# exp_w2v2t_ru_unispeech-ml_s253

Fine-tuned [microsoft/unispeech-large-multi-lingual-1500h-cv](https://huggingface.co/microsoft/unispeech-large-multi-lingual-1500h-cv) for speech recognition using the train split of [Common Voice 7.0 (ru)](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0).
When using this model, make sure that your speech input is sampled at 16kHz.

This model has been fine-tuned by the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) tool.