Respaired / RiFornet_Vocoder
a Neural Vocoder supporting Ring Attention, Conformer and NSF.
☆18Updated 2 months ago
Alternatives and similar repositories for RiFornet_Vocoder:
Users that are interested in RiFornet_Vocoder are comparing it to the libraries listed below
- The Vokan Architecture (Tsukasa speech based)☆9Updated 2 months ago
- ☆13Updated 8 months ago
- A collection of all our phonemeizers for dataset construction and inference☆22Updated 2 months ago
- GPT for FACodec☆13Updated last year
- My vocoder experiments☆28Updated 6 months ago
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆27Updated 8 months ago
- Temporary anonymous version☆22Updated last year
- Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks☆17Updated last year
- speaker-disentangled speech linguistic content quantizer☆11Updated last month
- Production-ready vocoder using BigVSAN☆11Updated last year
- Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"☆13Updated 2 weeks ago
- Collection of scripts from mHuBERT-147.☆24Updated 5 months ago
- Simple and lightweight Zero-shot Text-to-Speech (TTS) synthesis model☆20Updated 2 weeks ago
- DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors☆19Updated 2 months ago
- ☆10Updated 5 months ago
- ☆11Updated 2 years ago
- text to speech☆10Updated last year
- ESLTTS dataset☆16Updated 2 months ago
- Unofficial implementation of ConvNeXt-TTS powered by lightning☆17Updated 6 months ago
- Forced alignment decoder for Whisper.☆14Updated last year
- Dippy Synthetic Speech Subnet☆16Updated 3 weeks ago
- Code associated with the paper: CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition.☆14Updated last month
- 4G GPU & 10 Minutes for train☆12Updated last year
- Just another FastSpeech 2 but cleaner code :)☆26Updated 9 months ago
- ☆19Updated last year
- ☆24Updated last year
- SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.☆13Updated last year
- Speech Resynthesis and Language Modeling Using Flow Matching and Llama☆17Updated this week
- ☆35Updated last year
- Tidy Tunes is an easy-to-use pipeline for mining high-quality audio data for speech generation models. To do so, it chains multiple open …☆16Updated 2 weeks ago