y-chan / hifi-gan-misrnetLinks
unofficial pytorch implementation of HiFi-GAN with fast MISR.
☆15Updated 2 years ago
Alternatives and similar repositories for hifi-gan-misrnet
Users that are interested in hifi-gan-misrnet are comparing it to the libraries listed below
Sorting:
- Phonemes and durations labeling based on whisper small☆11Updated 11 months ago
- ☆12Updated 2 years ago
- ☆19Updated last year
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆27Updated 10 months ago
- Unofficial implementation of ConvNeXt-TTS powered by lightning☆17Updated 8 months ago
- Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks☆17Updated last year
- text to speech☆10Updated last year
- Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"☆12Updated 2 months ago
- ☆10Updated 7 months ago
- ☆11Updated 4 months ago
- A TTS Trained on Universal Audio.☆34Updated 2 weeks ago
- LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM☆16Updated last year
- Speech Resynthesis and Language Modeling☆18Updated 2 weeks ago
- An evaluation set for large-scale trained TTS models (Coming in Sep 2024)☆12Updated 9 months ago
- Production-ready vocoder using BigVSAN☆11Updated last year
- GPT for FACodec☆13Updated last year
- End-to-End SpeechSynthesis system with fastspeech2 & hifigan☆13Updated 2 years ago
- ☆19Updated 2 years ago
- 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 …☆21Updated 3 weeks ago
- ☆16Updated 3 years ago
- NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates [WIP]☆24Updated 2 years ago
- 60k hours of phoneme-aligned audio from audio books☆18Updated 10 months ago
- A robust pitch tracker using synchro-squeezed fft and frequency domain autocorrelation☆34Updated last year
- ☆13Updated last year
- Try to replicate the architecture of MiniMaxTTS mentioned in it's technical report☆33Updated last month
- ☆25Updated 2 years ago
- ☆13Updated 7 months ago
- ☆11Updated 2 years ago
- 22人で童謡を5曲ずつ歌ってつくった歌唱データベースです。☆13Updated 2 years ago
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆48Updated last year