haoheliu / SemantiCodec-inference
Ultra-low bitrate neural audio codec (0.31~1.40 kbps) with a better semantic in the latent space.
☆149Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for SemantiCodec-inference
- Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model☆104Updated last month
- The open source code for SimpleSpeech series☆111Updated last month
- UTokyo-SaruLab MOS Prediction System☆94Updated last week
- High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec☆80Updated last month
- FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3☆166Updated 7 months ago
- Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization☆160Updated 4 months ago
- Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)☆139Updated last year
- Reference-aware automatic speech evaluation toolkit☆109Updated 9 months ago
- [AAAI 2024] Code for CTX-vec2wav in UniCATS☆122Updated 5 months ago
- Audio Codec Speech processing Universal PERformance Benchmark☆220Updated 2 weeks ago
- Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"☆82Updated 2 months ago
- Real-time Speech-Text Foundation Model Toolkit (wip)☆122Updated last month
- LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning☆114Updated 5 months ago
- Official implementation of Vec-Tok Speech☆93Updated last year
- [ICASSP 2024] StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations☆135Updated 6 months ago
- ☆104Updated last month
- Training code for FAcodec presented in NaturalSpeech3☆178Updated 2 months ago
- The official implementation of EmoSphere-TTS☆85Updated 3 months ago
- SSR-Speech: Towards Stable, Safe and Robust Zero-shot Speech Editing and Synthesis☆97Updated 2 weeks ago
- ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations☆126Updated 8 months ago
- It's a repository for implementations of neural speech editing algorithms.☆191Updated 10 months ago
- Unofficial SoundStream implementation of Pytorch with training code and 16kHz pretrained checkpoint☆58Updated last year
- Train the next generation of TTS systems.☆161Updated 2 months ago
- Evaluation Protocol for Large-Scale Zero-Shot TTS Literature☆66Updated last month
- Audiogen Codec☆127Updated 4 months ago
- A sequence-to-sequence voice conversion toolkit.☆86Updated 4 months ago
- Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'☆88Updated 3 months ago
- Easy-to-Use Speech MOS predictors☆230Updated last year
- Pytorch implementation of BigVSAN☆198Updated 7 months ago
- AudioBench: A Universal Benchmark for Audio Large Language Models☆92Updated last week