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.
☆1,222Updated 2 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.☆1,328Updated 2 weeks ago
- Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.☆1,657Updated this week
- first base model for full-duplex conversational audio☆1,746Updated 6 months ago
- Local realtime voice AI☆2,330Updated 4 months ago
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆914Updated 8 months ago
- Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection☆763Updated last month
- Whisper with Medusa heads☆849Updated this week
- Real Time Speech Transcription with FastRTC ⚡️and Local Whisper 🤗☆665Updated this week
- Implementation of F5-TTS in MLX☆560Updated 3 months ago
- TTS with kokoro and onnx runtime☆2,079Updated 3 weeks ago
- ☆782Updated 2 months ago
- A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats includ…☆565Updated last week
- A Fast TTS Engine☆523Updated 5 months ago
- ☆610Updated 2 weeks ago
- Fast and accurate automatic speech recognition (ASR) for edge devices☆2,782Updated last month
- Run Orpheus 3B Locally With LM Studio☆432Updated 3 months ago
- High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and modern web UI. Optimized for RTX GPUs.☆463Updated last week
- 🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.☆548Updated 2 weeks ago
- https://hf.co/hexgrad/Kokoro-82M☆3,484Updated last week
- ☆498Updated 2 weeks ago
- Fast Streaming TTS with Orpheus + WebRTC (with FastRTC)☆298Updated 3 months ago
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆586Updated 3 months ago
- A fast multimodal LLM for real-time voice☆4,087Updated this week
- Controllable and fast Text-to-Speech for over 7000 languages!☆1,620Updated last week
- TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching☆756Updated last month
- Sesame CSM 1B Voice Cloning☆312Updated 3 months ago
- Realtime demo, Streaming and Finetuning code for CSM☆341Updated last month
- G2P☆272Updated 2 months ago
- ☆605Updated last week
- Towards Human-Sounding Speech☆5,196Updated 2 months ago