kyutai-labs / hibiki
Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.
☆926Updated last month
Alternatives and similar repositories for hibiki:
Users that are interested in hibiki are comparing it to the libraries listed below
- Interface for OuteTTS models.☆955Updated last month
- Local realtime voice AI☆2,260Updated 3 weeks ago
- first base model for full-duplex conversational audio☆1,722Updated 2 months ago
- A Fast TTS Engine☆472Updated 2 months ago
- Real Time Speech Transcription with FastRTC ⚡️and Local Whisper 🤗☆538Updated this week
- Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching☆2,112Updated this week
- Implementation of F5-TTS in MLX☆504Updated last week
- NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms☆840Updated this week
- Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection☆639Updated 3 months ago
- Fast and accurate automatic speech recognition (ASR) for edge devices☆2,640Updated 3 weeks ago
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆889Updated 4 months ago
- https://hf.co/hexgrad/Kokoro-82M☆1,825Updated last week
- ☆591Updated last week
- TTS Towards Human-Sounding Speech☆2,717Updated this week
- TTS with kokoro and onnx runtime☆1,789Updated 3 weeks ago
- Whisper with Medusa heads☆821Updated 3 weeks ago
- TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching☆690Updated 3 weeks ago
- A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple S…☆366Updated this week
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆473Updated last week
- Run Orpheus 3B Locally With LM Studio☆277Updated this week
- Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion☆1,268Updated this week
- An experiment in meeting transcription and diarization with just an LLM. Maybe I went a little overboard though☆528Updated last month
- InspireMusic: A Unified Framework for Music, Song, Audio Generation.☆1,000Updated last week
- 🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.☆448Updated this week
- Self-hosted voice chat with LLMs☆422Updated 3 weeks ago
- A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats includ…☆312Updated 2 weeks ago
- Local SRT/LLM/TTS Voicechat☆644Updated 5 months ago
- Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯☆822Updated 2 weeks ago
- G2P☆174Updated this week
- An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Spe…☆2,444Updated last month