skirdey / voicerestore
VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration
☆10Updated this week
Related projects: ⓘ
- Unofficial implementation of ConvNeXt-TTS powered by lightning and Rye☆12Updated 4 months ago
- Speech enhancement in noisy and reverberant environments using deep neural networks☆15Updated last month
- ☆14Updated 2 weeks ago
- Supervoice diffusion enhance☆24Updated 2 months ago
- ☆19Updated 5 months ago
- Viterbi decoding in PyTorch☆23Updated 3 weeks ago
- Official repository for NAST: Noise Aware Speech Tokenization for Speech Language Models (Interspeech 2024) https://arxiv.org/abs/2406.11…☆40Updated 2 months ago
- A neural speech codec based on discrete WavLM representations☆14Updated 3 weeks ago
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆27Updated last month
- Aligner for text-to-speech☆15Updated 2 months ago
- GPT for FACodec☆13Updated 5 months ago
- Production-ready vocoder using BigVSAN☆11Updated 7 months ago
- The TTSDS benchmark evaluates synthetic speech quality by considering prosody, speaker identity, and intelligibility, comparing these fac…☆14Updated 3 weeks ago
- Aty-TTS: Improving fairness for spoken language understanding in atypical speech with Text-to-Speech☆10Updated 9 months ago
- ☆13Updated 2 weeks ago
- VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling☆13Updated last month
- LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM☆16Updated 4 months ago
- Official implementation of paper: Frame-Wise Breath Detection with Self-Training: An Exploration of Enhancing Breath Naturalness in Text-…☆17Updated last month
- ☆21Updated this week
- ☆27Updated 6 months ago
- ☆24Updated 2 months ago
- Interface Design for Self-Supervised Speech Models, Accepted to Interspeech2024☆14Updated 2 months ago
- Unofficial implementation of wavenext vocoder☆28Updated 3 weeks ago
- ☆33Updated 5 months ago
- ☆28Updated this week
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆46Updated last year
- Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks☆17Updated last year
- ☆10Updated last month
- ESLTTS dataset☆15Updated 2 months ago