| language: | |
| - grn | |
| tags: | |
| - guarani | |
| - text-to-speech | |
| - speech | |
| - audio | |
| - vits | |
| license: mit | |
| # MMS-TTS Guarani Model | |
| This is a VITS-based text-to-speech model for the Guarani language, based on the MMS-TTS architecture. | |
| ## Model Description | |
| This model can generate speech from Guarani text input using the VITS architecture. | |
| ## Usage | |
| ```python | |
| from transformers import VitsModel, AutoTokenizer | |
| import torch | |
| model = VitsModel.from_pretrained("joselobenitezg/mms-grn-tts") | |
| tokenizer = AutoTokenizer.from_pretrained("joselobenitezg/mms-grn-tts") | |
| text = "some example text in the Guarani language" | |
| inputs = tokenizer(text, return_tensors="pt") | |
| with torch.no_grad(): | |
| output = model(**inputs).waveform | |
| # Save the output as a wav file | |
| import scipy | |
| scipy.io.wavfile.write("output.wav", rate=model.config.sampling_rate, data=output) | |
| ``` | |