xzf-thu / Mini-Omni-ReasonerLinks
Mini-Omni-Reasoner: a real-time speech reasoning framework that interleaves silent reasoning tokens with spoken response tokens (“thinking-in-speaking”), exploiting the LLM–audio throughput gap to keep speech fluent and low-latency while maintaining structured internal reasoning.
☆162Updated 4 months ago
Alternatives and similar repositories for Mini-Omni-Reasoner
Users that are interested in Mini-Omni-Reasoner are comparing it to the libraries listed below
Sorting:
- Code for paper "Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models"☆241Updated last year
- AudioTrust: Benchmarking the Multi-faceted Trustworthiness of Audio Large Language Models☆208Updated last month
- CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech☆364Updated 4 months ago
- PyTorch Implementation of TCSinger 2(ACL 2025): Customizable Multilingual Zero-shot Singing Voice Synthesis☆162Updated 2 months ago
- Code for paper "Large Language Models are Efficient Learners of Noise-Robust Speech Recognition"☆139Updated last year
- A Unified Framework for Expressive Speech Synthesis with Voice Cloning☆400Updated last month
- [ICML 2025] PyTorch Implementation of "OmniAudio: Generating Spatial Audio from 360-Degree Video"☆343Updated 6 months ago
- ☆159Updated 3 months ago
- Code for paper "GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators"☆198Updated last year
- GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling☆161Updated 10 months ago
- This is the demo of our paper "IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation".☆106Updated 9 months ago
- The first Large Audio Language Model that enables native in-depth thinking, which is trained on large-scale audio Chain-of-Thought data.☆274Updated 7 months ago
- PyTorch Implementation of TCSinger(EMNLP 2024): Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control☆370Updated 3 months ago
- Official code of ICML 2025 paper "NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Predicti…☆134Updated 2 months ago
- The official Soundwave repository☆225Updated 9 months ago
- PyTorch Implementation of StyleSinger(AAAI 2024): Style Transfer for Out-of-Domain Singing Voice Synthesis☆416Updated 4 months ago
- PyTorch Implementation of VersBand(EMNLP 2025): Versatile Framework for Song Generation with Prompt-based Control☆223Updated 4 months ago
- Official repo for WavCraft, an AI agent for audio creation and editing☆526Updated 10 months ago
- Single-blind supplementary materials for NeurIPS 2023 submission☆92Updated last year
- ☆14Updated 7 months ago
- A song aesthetic evaluation toolkit trained on SongEval.☆266Updated 6 months ago
- EvaLearn is a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in chall…☆430Updated 3 months ago
- [ICCV 2025] Official Implementation for "Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition"☆304Updated last year
- UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models☆110Updated 2 months ago
- Dataset and code of GTSinger(NeurIPS 2024 Spotlight): A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing…☆343Updated 4 months ago
- ☆52Updated last month
- ☆100Updated last month
- ☆144Updated 6 months ago
- Image and video Tokenizer/VAE selection guide, text and face reconstruction evaluation.☆133Updated last month
- Model analyzer in PyTorch☆90Updated 4 months ago