frothywater / kanade-tokenizerLinks
Kanade is a speech tokenizer that encodes speech into compact content tokens and global embeddings and decodes them back to mel spectrograms.
☆36Updated 3 weeks ago
Alternatives and similar repositories for kanade-tokenizer
Users that are interested in kanade-tokenizer are comparing it to the libraries listed below
Sorting:
- PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind☆62Updated 4 months ago
- Unofficial implementation of wavenext vocoder☆55Updated last year
- PyTorch implementation of WaveFit [2022, Google] which is one of SOTA lightweight/fast speech vocoders.☆62Updated 4 months ago
- Training code and dataset cleasing with Sidon☆73Updated 2 weeks ago
- DiFlow-TTS delivers low-latency zero-shot TTS via discrete flow matching and factorized speech tokens. A compact, open framework for fast…☆50Updated last week
- Extract phoneme-level timestamps from speeh audio.☆114Updated 2 weeks ago
- ☆44Updated last year
- T5Voice is a lightweight PyTorch implementation of T5-based text-to-speech synthesis, supporting both streaming and non-streaming speech …☆28Updated 2 months ago
- [ACL 2025] OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching☆44Updated 11 months ago
- Official implementation of the paper "Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus" acc…☆77Updated 2 years ago
- Speech Resynthesis and Language Modeling☆27Updated 7 months ago
- My vocoder experiments☆31Updated 6 months ago
- ☆49Updated 10 months ago
- [Interspeech 2025] Official implementation of "Training-Free Voice Conversion with Factorized Optimal Transport"☆43Updated 4 months ago
- Official Code for SyllableLM: Learning Coarse Semantic Units for Speech Language Models☆59Updated 7 months ago
- ☆52Updated 7 months ago
- [EMNLP 2025 Findings] Official code for EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion☆31Updated 4 months ago
- Speech Parameter Estimation Using Differentiable Speech Synthesizer☆44Updated 2 years ago
- Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis☆27Updated 10 months ago
- ☆32Updated 3 months ago
- A lightweight audio codec based on a single quantizer☆68Updated 5 months ago
- ☆14Updated 5 months ago
- AudioSR-Upsampling (any -> 48kHz)☆42Updated last year
- Official repository for NAST: Noise Aware Speech Tokenization for Speech Language Models (Interspeech 2024) https://arxiv.org/abs/2406.11…☆46Updated last year
- Streaming Vocos☆29Updated 7 months ago
- ☆70Updated last year
- ☆45Updated 6 months ago
- Variable Bitrate Residual Vector Quantization for Audio Coding☆50Updated 9 months ago
- Alignment examples for Interspeech 2024☆27Updated last year
- Official repository of Wavehax vocoder☆66Updated last month