Respaired / Tsukasa-SpeechLinks
a Frontier Japanese Speech Generation net
☆39Updated 3 weeks ago
Alternatives and similar repositories for Tsukasa-Speech
Users that are interested in Tsukasa-Speech are comparing it to the libraries listed below
Sorting:
- DDPM-based Pitch Generation and Pitch Controllable Voice Synthesis.☆53Updated last year
- StyleTTS 2 Optimized Training Fork☆29Updated 4 months ago
- High quality text-to-speech based on StyleTTS 2.☆48Updated last week
- 44100Hz日本語音源に対応させた unofficial vits2-TTS implementation in pytorchです。☆22Updated last year
- PyTorch implementation of WaveFit [2022, Google] which is one of SOTA lightweight/fast speech vocoders.☆55Updated 3 weeks ago
- 大量の音声データから笑い声部分を集めるやつ☆10Updated last year
- Coco-Nut (Corpus of connecting NIHONGO utterance and text) corpus☆22Updated 11 months ago
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆98Updated 7 months ago
- PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-To-Speech Using Natural Language Descriptions☆79Updated 7 months ago
- ☆47Updated 10 months ago
- Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"☆70Updated this week
- Fine-tuning Moshi/J-Moshi on your own spoken dialogue data☆56Updated last month
- VITS2 using Phoneme-Level Japanese BERT☆13Updated last year
- DEX-TTS: Diffusion-based EXpressive TTS with Style Modeling on Time Variability☆101Updated 4 months ago
- This repository contains the code and data for the paper EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control by Haozhe Chen,…☆73Updated 8 months ago
- A collection of all our phonemeizers for dataset construction and inference☆23Updated 3 months ago
- StyleTTS2 + Vocos as a Decoder☆12Updated 2 months ago
- ☆29Updated last year
- a lightweight voice conversion☆82Updated 9 months ago
- ☆50Updated 2 months ago
- ☆26Updated 7 months ago
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆69Updated 4 months ago
- A TTS Trained on Universal Audio.☆27Updated last week
- A repository of Japanese Phoneme-Level BERT☆22Updated last year
- An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io☆67Updated last year
- Simple and lightweight Zero-shot Text-to-Speech (TTS) synthesis model☆24Updated last month
- 44100Hz日本語HuBERTに対応した QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion です。☆14Updated 2 years ago
- ☆39Updated 8 months ago
- TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching☆58Updated last month
- All generative model in one for better TTS model☆71Updated 8 months ago