kyutai-labs / hibikiLinks
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.
☆1,262Updated 4 months ago
Alternatives and similar repositories for hibiki
Users that are interested in hibiki are comparing it to the libraries listed below
Sorting:
- Interface for OuteTTS models.☆1,375Updated 2 months ago
- first base model for full-duplex conversational audio☆1,755Updated 8 months ago
- Local realtime voice AI☆2,361Updated 6 months ago
- Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.☆2,326Updated last week
- Real Time Speech Transcription with FastRTC ⚡️and Local Whisper 🤗☆680Updated 2 months ago
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆918Updated 10 months ago
- Fast and accurate automatic speech recognition (ASR) for edge devices☆2,855Updated last week
- ☆909Updated this week
- A Fast TTS Engine☆542Updated 7 months ago
- Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection☆813Updated 3 months ago
- Whisper with Medusa heads☆853Updated last month
- Make text LLMs listen and speak☆859Updated last week
- Fast Streaming TTS with Orpheus + WebRTC (with FastRTC)☆308Updated 5 months ago
- ☆632Updated last month
- Implementation of F5-TTS in MLX☆581Updated 5 months ago
- LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve spee…☆3,068Updated 3 months ago
- Run Orpheus 3B Locally With LM Studio☆460Updated 5 months ago
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆611Updated 5 months ago
- Controllable and fast Text-to-Speech for over 7000 languages!☆1,637Updated 2 months ago
- High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and modern web UI. Optimized for RTX GPUs.☆549Updated 2 months ago
- G2P☆316Updated last month
- TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching☆781Updated last month
- TTS with kokoro and onnx runtime☆2,178Updated 2 months ago
- Local SRT/LLM/TTS Voicechat☆716Updated 11 months ago
- ☆834Updated 2 weeks ago
- A fast multimodal LLM for real-time voice☆4,181Updated last week
- ☆515Updated 3 weeks ago
- A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats includ…☆732Updated 3 weeks ago
- Towards Human-Sounding Speech☆5,536Updated 4 months ago
- NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms☆1,077Updated 4 months ago