Llama-Mimi is a speech language model that uses a unified tokenizer (Mimi) and a single Transformer decoder (Llama) to jointly model sequences of interleaved semantic and acoustic tokens.
☆31Sep 20, 2025Updated 11 months ago
Alternatives and similar repositories for llama-mimi
Users that are interested in llama-mimi are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- JAX implementation of Large Language Models. You can train GPT-2-like model with 青空文庫 (aozora bunko-clean dataset) or any other text dat…☆13Aug 5, 2024Updated 2 years ago
- ☆34Aug 6, 2026Updated last month
- Official implementation of "Wave-Trainer-Fit: Neural Vocoder with Trainable Prior and Fixed-Point Iteration towards High-Quality Speech G…☆16Feb 6, 2026Updated 7 months ago
- Official Pytorch implementation of "Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models" [IEEE ICASSP 202…☆37Aug 20, 2026Updated 2 weeks ago
- Multi-talker ASR based on DiCoW with Serialized Output Training☆21Sep 18, 2025Updated 11 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆31Aug 18, 2026Updated 2 weeks ago
- A variable-frame-rate 16 kHz speech codec based on FocalCodec☆21Feb 11, 2026Updated 6 months ago
- PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind☆70Sep 22, 2025Updated 11 months ago
- ☆28Aug 1, 2026Updated last month
- An attempt to reproduce CALM (Continuous Audio Language Models) using DACVAE as the audio VAE.☆19Feb 20, 2026Updated 6 months ago
- [ICLR 2026] StableToken: A state-of-the-art noise-robust semantic speech tokenizer featuring Voting-LFQ for resilient SpeechLLMs.☆34Feb 27, 2026Updated 6 months ago
- ☆12Mar 11, 2025Updated last year
- fd-sds☆21Apr 8, 2026Updated 4 months ago
- VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency and Speaking rate Control☆250May 30, 2026Updated 3 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ICLR2026] FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates☆52Aug 20, 2026Updated 2 weeks ago
- Kanade is a single-layer disentangled speech tokenizer that extracts compact tokens suitable for both generative and discriminative model…☆115Jul 18, 2026Updated last month
- ☆15Aug 6, 2026Updated last month
- ☆54Jul 5, 2026Updated 2 months ago
- ☆21Mar 6, 2026Updated 6 months ago
- The official repository TimeAudio, a comprehensive framework that incorporates fine-grained acoustic cues into LALMs with enhanced module…☆31Nov 18, 2025Updated 9 months ago
- ☆48Jul 7, 2025Updated last year
- A neural speech codec based on discrete WavLM representations☆26Aug 28, 2024Updated 2 years ago
- Onset-and-Offset-Aware Sound Event Detection☆22Feb 10, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- LoRA-based phoneme/prosody control for LLM-based TTS with no G2P - Lightweight adapter for edit and control the target language's phoneme…☆29Jul 8, 2026Updated last month
- ☆19Oct 9, 2025Updated 10 months ago
- ☆40Apr 3, 2025Updated last year
- Demo for AudioSAE paper☆16Apr 26, 2026Updated 4 months ago
- [ACL 2025] Predicting Turn-Taking and Backchannel in Human-Machine Conversations Using Linguistic, Acoustic, and Visual Signals☆35Aug 11, 2025Updated last year
- [ASRU 2025] Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?☆48Nov 21, 2025Updated 9 months ago
- ☆21Apr 9, 2026Updated 4 months ago
- Fine-tuning Moshi/J-Moshi on your own spoken dialogue data☆105Jan 5, 2026Updated 8 months ago
- ☆23Sep 14, 2025Updated 11 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Eureka-Audio: A 1.7B lightweight audio–language model that matches 7B–30B models on ASR, audio understanding, and paralinguistic reasonin…☆44Apr 11, 2026Updated 4 months ago
- Easily turn large English text datasets into Japanese text datasets using open LLMs.☆32Jan 20, 2025Updated last year
- This is the official code for ACM CIKM 2025 Paper: ParaStyleTTS: Toward Efficient and Robust Paralinguistic Style Control for Expressive …☆60Dec 21, 2025Updated 8 months ago
- open-vocabulary sound event detection☆56Dec 17, 2025Updated 8 months ago
- Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation☆75Jun 16, 2026Updated 2 months ago
- JATTS: A modern, research-oriented Japanese Text-to-speech Open-sourced Toolkit☆44Mar 13, 2026Updated 5 months ago
- [AAAI 2026 & ACL 2026] The official implementation of the DIFFA series for dLLM-based large audio language model☆84Apr 7, 2026Updated 5 months ago