kyutai-labs / delayed-streams-modelingLinks
Delayed Streams Modeling (DSM) is a flexible formulation for streaming, multimodal sequence-to-sequence learning.
☆211Updated this week
Alternatives and similar repositories for delayed-streams-modeling
Users that are interested in delayed-streams-modeling are comparing it to the libraries listed below
Sorting:
- ☆238Updated 2 months ago
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆84Updated last month
- Collection of Open Source Speech Data☆159Updated 7 months ago
- Kyutai with an "eye"☆200Updated 2 months ago
- A simple, hackable text-to-speech system in PyTorch and MLX☆164Updated 4 months ago
- Streaming and Fine-tuning for Chatterbox TTS☆99Updated last week
- Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers☆56Updated last month
- Open TTS models, built for streaming on the edge☆43Updated 3 months ago
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆62Updated 3 weeks ago
- VoiceStar: Robust, Duration-controllable TTS that can Extrapolate☆258Updated 3 weeks ago
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆174Updated 2 months ago
- VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration☆173Updated 2 months ago
- A random walk voice style cloning application for Kokoro text to speech☆98Updated this week
- G2P☆258Updated last month
- Official implementation of the TTS model Lina-Speech☆165Updated 5 months ago
- Automatically cleaning, enhancing, segmenting, filtering, and formatting a dataset to fine tune or train a voice model.☆38Updated last week
- ☆188Updated last month
- Audio tokenization, in the fastest way possible!☆52Updated 9 months ago
- ☆181Updated this week
- Joint speech-language model - respond directly to audio!☆30Updated last year
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆104Updated last month
- ☆397Updated this week
- Real-time Speech-Text Foundation Model Toolkit (wip)☆237Updated 2 months ago
- ☆62Updated 10 months ago
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆258Updated last month
- python bindings for symphonia/opus - read various audio formats from python and write opus files☆64Updated last month
- LlamaVoice is a llama-based large voice generation model, providing inference and training ability.☆233Updated 9 months ago
- Speaker Diarization with Transformers☆67Updated 2 weeks ago
- List of curated use cases built using Sesame's CSM 1B☆66Updated 3 weeks ago
- Efficient approach to speaker diarization using voice characteristics extraction☆96Updated this week