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.
☆1,351Updated 8 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.☆1,419Updated 6 months ago
- Local realtime voice AI☆2,426Updated last month
- first base model for full-duplex conversational audio☆1,769Updated last year
- Whisper with Medusa heads☆864Updated 5 months ago
- ☆1,189Updated last month
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆926Updated last year
- Real Time Speech Transcription with FastRTC ⚡️and Local Whisper 🤗☆692Updated 6 months ago
- Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection☆884Updated 7 months ago
- Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.☆2,703Updated last month
- Fast and accurate automatic speech recognition (ASR) for edge devices☆3,065Updated last month
- A Fast TTS Engine☆606Updated 11 months ago
- Make text LLMs listen and speak☆1,068Updated 2 weeks ago
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆643Updated 9 months ago
- Implementation of F5-TTS in MLX☆603Updated 9 months ago
- Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages☆2,556Updated last week
- 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…☆3,114Updated 7 months ago
- Local SRT/LLM/TTS Voicechat☆748Updated last year
- ☆635Updated 2 months ago
- G2P☆383Updated 5 months ago
- ☆533Updated 3 months ago
- Controllable and fast Text-to-Speech for over 7000 languages!☆2,143Updated 6 months ago
- Open source inference code for Rev's model☆435Updated 8 months ago
- TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching☆811Updated 5 months ago
- ☆1,356Updated 8 months ago
- A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats includ…☆1,069Updated 3 weeks ago
- Run Orpheus 3B Locally With LM Studio☆505Updated 9 months ago
- Fast Streaming TTS with Orpheus + WebRTC (with FastRTC)☆347Updated 9 months ago
- TTS with kokoro and onnx runtime☆2,326Updated 3 weeks ago
- High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and modern web UI. Optimized for RTX GPUs.☆630Updated 6 months ago
- The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trai…☆2,841Updated this week