yweweler / single-speaker-tts
This is a single-speaker neural text-to-speech (TTS) system capable of training in a end-to-end fashion. It is inspired by the Tacotron archicture and able to train based on unaligned text-audio pairs.
☆13Updated 6 years ago
Alternatives and similar repositories for single-speaker-tts:
Users that are interested in single-speaker-tts are comparing it to the libraries listed below
- Implementation of "FastSpeech: Fast, Robust and Controllable Text to Speech"☆51Updated 4 years ago
- A pytroch implementation of the FB-MelGAN☆88Updated 4 years ago
- Text to Speech Synthesis based on controllable latent representation☆14Updated 5 years ago
- Implementation of the AlignTTS☆76Updated last year
- ☆22Updated 5 years ago
- multilingual speech aligner☆73Updated last year
- ☆64Updated 2 years ago
- Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion☆39Updated 2 years ago
- Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing☆69Updated 2 years ago
- ☆25Updated 5 months ago
- RawNet: Fast End-to-End Neural Vocoder☆42Updated 5 years ago
- Pytorch implementation of "f0-consistent many-to-many non-parallel voice conversion via conditional autoencoder"☆28Updated 4 years ago
- An unofficial implementation of https://arxiv.org/abs/2005.05106☆46Updated 3 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 4 years ago
- Pitch estimation network (PiENet) for noise-robust neural F0 estimation of speech signals☆50Updated 5 years ago
- an tutorial implement of voice conversion using pytorch☆35Updated 6 years ago
- ☆27Updated last year
- follow NVIDIA, simplify it and support data parallel.☆13Updated 5 years ago
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis☆41Updated 3 years ago
- [IJCAI'23] Learning to Speak from Text for Low-Resource TTS☆64Updated last year
- ☆36Updated 3 years ago
- Conditional Variational Auto-Encoder with Jointly Training FastSpeech2(+Conformer) and HiFi-GAN for End to End Text to Speech☆46Updated 2 years ago
- Labels for kiritan_singing data with extra resources for DNN-based singing voice synthesis (SVS) systems.☆29Updated last year
- Implementation of DCTTS with Adversarial Training☆12Updated 5 years ago
- Implementation of Global Style Token Tacotron in TensorFlow2☆25Updated 4 years ago
- Implementation of "FastSpeech: Fast, Robust and Controllable Text to Speech"☆64Updated last year
- Implementation of Multi speaker TTS☆50Updated 4 years ago
- ☆91Updated 3 years ago
- wavenet vocoder using tensorflow☆27Updated 6 years ago
- Implementation of the paper "BERTphone: Phonetically-aware Encoder Representations for Utterance-level Speaker and Language Recognition"☆17Updated 4 years ago