kaiidams / Kokoro-Speech-Dataset
A public domain single speaker Japanese speech dataset
☆38Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Kokoro-Speech-Dataset
- context labels and pronunciation data for JSUT corpus☆67Updated 3 years ago
- ☆33Updated 2 years ago
- DDPM-based Pitch Generation and Pitch Controllable Voice Synthesis.☆51Updated last year
- Official implementation of the source-filter HiFiGAN vocoder☆234Updated last year
- ☆83Updated 3 years ago
- HTS-style full-context labels for JSUT v1.1☆46Updated 3 years ago
- JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech☆104Updated 2 years ago
- Coco-Nut (Corpus of connecting NIHONGO utterance and text) corpus☆21Updated 5 months ago
- ☆213Updated last year
- A repository of Japanese Phoneme-Level BERT☆20Updated 11 months ago
- xvector model on jtubespeech☆40Updated last year
- Python wrapper for OpenJTalk☆203Updated 4 months ago
- Monotonic Alignment Search☆86Updated 2 years ago
- A fork of open_jtalk☆53Updated 4 months ago
- 44100Hz 日本語音源に対応させた unofficial vits2-TTS implementation in pytorchです。☆22Updated last year
- ☆42Updated 3 months ago
- An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"☆26Updated 7 months ago
- ☆18Updated 3 years ago
- 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 last year
- Easy-to-Use Speech MOS predictors☆230Updated last year
- tdmelodic for open-jtalk☆22Updated 3 years ago
- ☆101Updated last month
- A Japanese accent dictionary generator☆112Updated 8 months ago
- Singing Voice Synthesis based on VITS, different from VISinger☆187Updated last year
- NVIDIA's FastPitch, extracted from the DeepLearningExamples repository☆11Updated 7 months ago
- ☆32Updated last year
- ☆254Updated last year
- JVS (Japanese versatile speech) コーパスの自作のラベル☆31Updated 3 years ago
- A differentiable version of SPTK☆166Updated this week