Massively Multilingual Speech (MMS): Kurdish, Northern Text-to-Speech This repository contains the Kurdish, Northern (kmr-script_arabic) language text-to-speech (TTS) model checkpoint. This model is part of Facebook's Massively Multilingual Speech project, aiming…

Massively Multilingual Speech (MMS): Ukrainian Text-to-Speech This repository contains the Ukrainian (ukr) language text-to-speech (TTS) model checkpoint. This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology…

Massively Multilingual Speech (MMS): Udmurt Text-to-Speech This repository contains the Udmurt (udm) language text-to-speech (TTS) model checkpoint. This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology…

Massively Multilingual Speech (MMS): Portuguese Text-to-Speech This repository contains the Portuguese (por) language text-to-speech (TTS) model checkpoint. This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology…

Vocoder with HiFIGAN trained on LJSpeech This repository provides all the necessary tools for using a HiFIGAN vocoder trained with LJSpeech. The pre-trained model takes in input a spectrogram and produces…

tts_transformer-tr-cv7 Transformer text-to-speech model from fairseq S^2 (paper/code): Turkish Single-speaker male voice Trained on Common Voice v7 Usage from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub from fairseq.models.text_to_speech.hub_interface import…

ESPnet2 TTS pretrained model kan-bayashi/ljspeech_vits ♻️ Imported from https://zenodo.org/record/5443814/ This model was trained by kan-bayashi using ljspeech/tts1 recipe in espnet. Demo: How to use in ESPnet2 # coming soon Citing ESPnet @inproceedings{watanabe2018espnet, …

tts_transformer-mn-mbspeech Transformer text-to-speech model from fairseq S^2 (paper/code): Mongolian Single-speaker male voice Trained on MBSpeech Source link