| title | emoji | colorFrom | colorTo | sdk | sdk_version | app_file | pinned |
|---|---|---|---|---|---|---|---|
Ukrainian Speech-to-Text |
🐌 |
blue |
yellow |
gradio |
3.41.2 |
app.py |
false |
This is a repository with aim to apply various speech recognition models on Ukrainian language.
You can see online demo here: https://huggingface.co/spaces/robinhad/ukrainian-stt.
Github link: https://github.com/robinhad/voice-recognition-ua.
Source code is in this repository together with auto-deploy pipeline scripts.
| Model name | CER | WER | License | Note |
|---|---|---|---|---|
| Wav2Vec2 | 6,01% | 27,99% | MIT | Common Voice 8 dataset, test set used as validation |
| DeepSpeech with Wiki LM | 12% | 30,65% | CC-BY-NC 4.0 | Common Voice 6 dataset |
| DeepSpeech | 16% | 57% | CC-BY-NC 4.0 | Common Voice 6 dataset |
Checkout latest releases here: https://github.com/robinhad/voice-recognition-ua/releases/.
If you'd like to check out different models for Ukrainian language, please visit https://github.com/egorsmkv/speech-recognition-uk.
Guides for training are available in corresponding folders for each model.
If you like my work, please support here: https://send.monobank.ua/jar/48iHq4xAXm
@robinhad - model training.
@egorsmkv - organized Ukrainian Speech recognition community.
@tarasfrompir - created synthetic 1200h Ukrainian Speech-to-Text dataset.
@AlexeyBoiler - hosted Ukrainian Speech-to-Text dataset.