# Model card for alma (medium)

* Language: sv_SE (Swedish, Sweden)
* Speakers: 1
* Quality: medium
* Samplerate: 22,050Hz
* URL: https://huggingface.co/yeagersthlm/piper-voice-sv-alma

## License

The model weights are released under CC BY 4.0, following the license of the NST training data.

## Training

Trained on the NST Swedish TTS Dataset (Språkbanken, National Library of Norway). The dataset contains high-quality studio recordings of Swedish speech.