KdaiP / conformer-RoPELinks
Conformer block with Rotary Position Embedding, modified from lucidrains' implement
☆16Updated last year
Alternatives and similar repositories for conformer-RoPE
Users that are interested in conformer-RoPE are comparing it to the libraries listed below
Sorting:
- ☆19Updated last year
- ☆11Updated 10 months ago
- Unofficial implementation of ConvNeXt-TTS powered by lightning☆16Updated 11 months ago
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆26Updated last year
- ☆19Updated last year
- ☆44Updated 2 months ago
- My vocoder experiments☆31Updated 2 months ago
- Official repository of Wavehax vocoder☆53Updated 2 months ago
- GPT for FACodec☆13Updated last year
- speaker-disentangled speech linguistic content quantizer☆22Updated 6 months ago
- Official repository for NAST: Noise Aware Speech Tokenization for Speech Language Models (Interspeech 2024) https://arxiv.org/abs/2406.11…☆46Updated last year
- Sequence alignement methods with helpers for PyTorch.☆24Updated 2 years ago
- PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind☆50Updated last week
- A robust pitch tracker using synchro-squeezed fft and frequency domain autocorrelation☆35Updated last year
- ☆48Updated 3 months ago
- An AR+AR TTS attempt.☆17Updated 8 months ago
- source code of EfficientTTS 2☆19Updated last year
- Temporary anonymous version☆22Updated last year
- A collection of all our phonemeizers for dataset construction and inference☆26Updated 7 months ago
- ☆14Updated 2 months ago
- Text-To-Speech for NotebookLM☆35Updated 2 months ago
- Official repo for DisCoder: High-Fidelity Music Vocoder using Neural Audio Codecs presented at ICASSP 2025☆33Updated 7 months ago
- AudioSR-Upsampling (any -> 48kHz)☆41Updated last year
- Unofficial implementation of wavenext vocoder☆50Updated last year
- ☆25Updated last year
- Variable Bitrate Residual Vector Quantization for Audio Coding☆49Updated 5 months ago
- LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM☆18Updated last year
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆48Updated 2 years ago
- Just another FastSpeech 2 but cleaner code :)☆27Updated last year
- HiFTNet wav/audio super-resolution 16/24 kHz to 48 kHz☆24Updated last year