kyutai-labs / moshi-webrtcLinks
Proof of concept for running moshi/hibiki using webrtc
☆19Updated 8 months ago
Alternatives and similar repositories for moshi-webrtc
Users that are interested in moshi-webrtc are comparing it to the libraries listed below
Sorting:
- Rust crate for some audio utilities☆25Updated 8 months ago
- python bindings for symphonia/opus - read various audio formats from python and write opus files☆70Updated 3 months ago
- implement llava using candle☆15Updated last year
- A small rust-based data loader☆31Updated 5 months ago
- GGML implementation of BERT model with Python bindings and quantization.☆56Updated last year
- Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.☆88Updated this week
- Joint speech-language model - respond directly to audio!☆30Updated last year
- ☆25Updated 11 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated 3 weeks ago
- ☆43Updated last month
- ☆13Updated 9 months ago
- Fast and versatile tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and…☆37Updated last month
- Rust implementation of Surya☆63Updated 8 months ago
- GPU accelerated client-side embeddings for vector search, RAG etc.☆65Updated last year
- Open TTS models, built for streaming on the edge☆44Updated 7 months ago
- Website with current metrics on the fastest AI models.☆42Updated last year
- Open-source reproducible benchmarks from Argmax☆66Updated last week
- Simple high-throughput inference library☆149Updated 6 months ago
- AnyModal is a Flexible Multimodal Language Model Framework for PyTorch☆102Updated 10 months ago
- Inference engine for GLiNER models, in Rust☆76Updated last week
- GPT-4 Level Conversational QA Trained In a Few Hours☆65Updated last year
- PyLate efficient inference engine☆66Updated 2 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- ☆51Updated 9 months ago
- A lightweight end-of-utterance detection model fine-tuned on SmolLM2-135M, optimized for Raspberry Pi and low-power devices.☆35Updated last week
- Aana SDK is a powerful framework for building AI enabled multimodal applications.☆53Updated 2 months ago
- ☆86Updated 4 months ago
- Trace LLM calls (and others) and visualize them in WandB, as interactive SVG or using a streaming local webapp☆14Updated 8 months ago
- Tokun to can tokens☆18Updated 4 months ago
- Training Models Daily☆16Updated last year